1 Introduction

Designing and developing products or services for the tourist industry are a complex undertaking that requires careful consideration of several factors before making any decisions [1]. A delicate balance is necessary among the many criteria, objectives, and restrictions stakeholders face in this area [2]. However, the challenge becomes even more daunting when designing and executing tourist attractions tailored to meet the demands and preferences of older and middle-aged tourists in today's market [3]. The varied and ever-changing nature of today's tourist economy adds another layer of complexity to the problems posed by this demographic [4]. A sophisticated comprehension of middle-aged and senior travellers' changing expectations, tastes, and needs is essential when catering to this demographic [5]. Comfort, convenience, and cultural resonance are generally sought-after by this cohort, in contrast to younger demographic groups [6]. In addition, their travel selections are greatly influenced by issues, such as mobility constraints [7], health concerns [8], and a strong desire for cultural immersion [9].

Recognizing and incorporating complexity into the design and development process are difficult for the tourist sector, especially for elderly travellers [10]. The tourist product’s design process entails ensuring that services are tailored to each individual, providing accessible accommodations, and assembling age-appropriate activities [11]. Consumer tastes, new technologies, and worldwide social and economic trends are all factors in the dynamic ecology in which the industry works [12]. To compete in a congested environment, stakeholders must stay current, anticipate market trends, and innovate [13]. This study is driven by the need to meet middle-aged and older travellers' changing demands and preferences in an ever-changing and diverse tourist scene. The study's overarching goal is to promote more welcoming, accessible, and satisfying travel experiences for older travellers worldwide by investigating novel approaches, using state-of-the-art technology [14], and learning more about the distinct traits of this age group.

The demand for products and services tailored to the specific needs and preferences of the middle-aged and senior population has experienced a notable increase within the tourism business. This particular demographic cohort frequently exhibits unique demands and anticipations in relation to their travel encounters. Nevertheless, the work of creating and constructing tourism products that adequately cater to these varied requirements can be arduous due to the inherent ambiguities and inaccuracies involved. The studies sought to address this difficulty by creating a decision support system that integrates fuzzy logic, a robust method for managing ambiguity and vagueness. The suggested approach can effectively capture and analyze the subjective and qualitative aspects that influence the design and development of middle-aged and senior tourism products by incorporating fuzzy logic into the decision-making process. The primary objective of this study is to provide a methodical and effective strategy that empowers the tourism sector to develop customized offerings that augment the travel encounters of this expanding generation, ultimately resulting in heightened levels of consumer contentment and allegiance.

This study explores using an FDSS [15] to tackle the challenges of tailoring tourist experiences to middle-aged and older people. The discovery of the complex and unpredictable nature of meeting the varied requirements of middle-aged and senior travellers within the tourism industry is the driving force behind this inquiry. Middle-aged and elderly tourism products are the framework that this study introduces. Developed on the principles of fuzzy logic [16], the fuzzy decision support system aims to make tourism more engaging and accessible for people of all ages. It draws on data on demographics, travel preferences, availability, and cultural sensitivity to truly magical design experiences [17]. A versatile decision-making method for middle-aged and elderly travellers was created in the METP–FDSS framework using fuzzy logic principles [18]. Tourism experiences that are immersive, inclusive, and personalized are the goal of this strategy. The framework enhances the effectiveness of decision support systems, accessibility, and customer satisfaction in producing tourist products. In addition, it delves into user experience, ROI, market competitiveness, and social and environmental effects and expands our understanding of tourism for middle-aged and older people.

The study's main contribution is the recommendation to use fuzzy decision support system (FDSS) to help design one-of-a-kind tourist experiences for people in their middle-aged and older years. The study's overarching goal is to accommodate the changing tastes and demands of the elderly by making the complex modern tourist business more welcoming and enjoyable for all. This study makes a significant contribution by taking a multi-faceted strategy to solving the problems and complications of creating tourist products for people in their middle-aged and older years. This study thoroughly investigates and analyzes the topic of middle-aged and senior tourism, making substantial contributions to the subject. The main benefits of this research include.

  • To introduce the METP–FDSS framework, combining fuzzy logic principles with demographic and travel insights, offers a systematic approach to creating inclusive tourism experiences for middle-aged and elder travellers.

  • To highlight the application of an FDSS model in guiding the design and development of the METP–FDSS framework to enhance product efficiency, customer satisfaction, and market competitiveness through fuzzy logic principles.

  • To evaluate the efficacy of the proposed METP–FDSS framework in enhancing customer satisfaction, accessibility, user experience, return on investment, market competitiveness, and social and environmental impact for older demographics.

The rest of this paper is organized as follows: Sect. 2 analyzes various tourism product design development studies. Section 3 projects the research design of the proposed METP–FDSS model. The design and development of the proposed METP–FDSS framework are described in Sect. 4. The evaluation and analysis of the METP–FDSS compared to other fuzzy-based models are presented in Sect. 5. Finally, Sect. 6 presents the conclusion summary with limitations and future research directions.

2 Literature Review

This study's literature review part explores previous studies that have examined different aspects of tourist management and customer behaviour. This review sheds light on the intricacies and dynamics of the tourist business by examining foundational works on the subject, as shown in Table 1.

Table 1 Existing research works on tourism product development
Full size table

Several facets of tourist management and customer behaviour are explored in the literature review. While Ma et al. [19] examined the dynamics of the green tourist supply chain, they focused on the best ways to make decisions and neglected to include behavioural factors or sustainability. While Azinuddin et al. [20] did note a favourable association between ecotourism architecture and environmentally conscious actions, they did not offer any concrete solutions. Community tourism using Nuanmeesri's [21] gamification strategy had good results, but there were problems with user uptake and long-term effects. While Sung et al. [23] emphasized the significance of green trust and the theory of planned behavior in decision-making, Fakfare et al. [22] investigated domestic tourism motivation. The importance of age, health state, and personal preferences in travel motivation and satisfaction was found by Zhong et al. [24] in their study of elderly tourists. Research limitations in comprehending cultural variations and influencer content were identified by Pop et al. [25] when they analyzed social media influencers. Though they created a context-aware tourist recommendation system, Abbasi-Moud et al. [26] found that it lacked generalizability and had no lasting effect.

Research on the green tourism supply chain has shown a favourable relationship between ecotourism architecture and environmentally conscious actions, as well as managerial insights and decision-making methods. However, there are still gaps in the combination of sustainability and behavioural issues. Although gamification has shown promising results in community tourism, questions about sustainability and user uptake persist. Research on domestic tourists' motivations highlights cultural variations and influencer material, while studies on green trust and the theory of planned behavior shed light on international tourists. There are some limits to the newly built context-aware tourism recommendation system. Customer happiness, accessibility, and decision-making methods can all be improved with the help of the suggested METP–FDSS framework, which provides a systematic process for building bespoke tourism experiences. Validating the system in different situations, improving the user experience, and discovering dynamic adaption mechanisms for ecotourism should all be priorities for future studies.

3 Research Design of the METP–FDSS Framework

A systematic method for designing and delivering tailored tourism experiences for middle-aged and elderly visitors is involved in the research development of the suggested middle-aged and elderly tourism products based on the fuzzy decision support system framework. Several essential components of the design are centered on the idea of using fuzzy logic principles to tailor tourist goods to the specific tastes and requirements of the elderly.

3.1 Conceptual Framework Development

 Beginning with the detailed development of an all-encompassing conceptual framework, our research will lay the groundwork for middle-aged and elderly tourism products Based on the fuzzy decision support system platform. Crafted with great care, this foundational framework captures the essence of serving middle-aged and elderly travellers by synthesizing numerous insights from multiple disciplines. The METP–FDSS model's conceptual basis is \(CF\). As demonstrated in Eq. (1), it is built by combining knowledge from several fields:

$${\text{CF}}={\text{Synthesis}}(\mathrm{Demographic\, Insights},\mathrm{Travel\, Preferences},\mathrm{ Accessibility\, Considerations},\mathrm{Cultural\, Sensitivities})$$
(1)

The core of this model is an investigation of demographic subtleties, which goes beyond simple age classifications to probe the complexities of personal preferences, socioeconomic status, and lifestyle variables that substantially impact travel patterns among the elderly. The study explores the human diversity within these age groups, recognizing that their travel experiences are shaped by their diverse needs and objectives. The variables in Eq. (2) that affect people's travel habits are their personal preferences (\(P\)), their socioeconomic status (\(E\)), and their way of life (\(L\)):

$$\mathrm{Demographic\, Insights}={\text{Explore}}(P,E,L)$$
(2)

In addition, the proposed model deftly negotiates complex travel preferences, considering that senior citizens are looking for one-of-a-kind adventures that speak to their values and goals in life. Tourism products that appeal to middle-aged and older travellers must consider their nuanced preferences to provide memorable experiences, whether seeking tranquil nature getaways or exciting cultural adventures. As shown in Eq. (3), elder travellers' travel preferences (\({\text{TP}}\)) include diversified experiences (\({E}_{{\text{exp}}}\)):

$${\text{TP}}={\text{Understand}}(E\_{\text{exp}})$$
(3)

Furthermore, the proposed model carefully incorporates accessibility factors, acknowledging that elderly tourists may have difficulties negotiating public spaces, means of transportation, and lodging establishments. The goal is to ensure that people with all mobility issues can enjoy tourist attractions by incorporating their feedback into accessibility features. The problems with physical spaces (\({\text{PS}}\)), transportation alternatives (\({\text{TO}}\)), and accommodation facilities (\({\text{AF}}\)) are addressed by accessibility characteristics (\({\text{AF}}\)), as shown in the following equation:

$${\text{AF}}={\text{Integrate}}({\text{PS}},{\text{TO}},{\text{AF}})$$
(4)

Furthermore, the model explores the complexities of cultural sensitivities, considering that elder tourists may have different cultural origins, views, and values that impact their actions when travelling. Understanding and respecting these cultural subtleties are crucial to creating tourist goods that connect with middle-aged and older travellers' varied identities and histories. Understanding the impact of different cultural backgrounds, beliefs, and values (\(B, {\text{VB}}, {\text{and}} V\)) on travel behaviours is crucial for cultural sensitivities (\({\text{CS}}\)), as shown in the following equation:

$${\text{CS}}={\text{Respect}}(B,V)$$
(5)

The conceptual framework of this study does a dual duty: it lays the groundwork for the METP–FDSS model. Combining these many aspects provides a solid theoretical basis for our future study. Within senior tourism, it acts as a compass, leading us to investigate the intricate interaction of demographics, travel preferences, accessibility concerns, and cultural sensitivities. As shown in Eqs. (6) and (7), the conceptual framework (\({\text{CF}}\)) combines insights related to demographics, preferences, accessibility, and culture:

$${\text{CF}}={\text{Synthesis}}(\mathrm{Demographic\, Insights},\mathrm{Travel\, Preferences},\mathrm{ Accessibility\, Considerations},\mathrm{Cultural\, Sensitivities})$$
(6)
$${\text{CF}}={\text{Compass}}(\mathrm{Demographic\, Factors},{\text{Preferences}},{\text{Accessibility}},\mathrm{Cultural\, Sensitivities})$$
(7)

The proposed framework provides a comprehensive view of the tourist industry's ever-changing landscape, essential for nuanced knowledge of older generations' varied requirements and preferences. The development of inclusive, engaging tourist experiences for older visitors can be guided by a comprehensive understanding of their needs, as shown in the following equation:

$${\text{Framework}}={\text{Empower}}({\text{Understanding}},{\text{Creativity}},{\text{Insight}})$$
(8)

It equips us to tackle the challenges of serving middle-aged and senior travellers with empathy, imagination, and understanding, aiming to make life-changing tourism experiences for everyone. To improve the tourism experiences of middle-aged and senior travellers, the conceptual framework for the METP–FDSS model is outlined, emphasizing integrating demographic insights, travel preferences, accessibility considerations, and cultural sensitivity.

3.2 Data Collection

The research methodology is designed to gather and analyze data thoroughly to understand the target demographic's preferences, actions, and expectations regarding tourism experiences. It uses a mix of primary and secondary data-gathering techniques, chosen for their ability to systematically capture the nuanced viewpoints and experiences of the middle-aged and older tourist population. Engaging with middle-aged and senior travelers, the research uses primary data collection methods, such as questionnaires, interviews, and focus group discussions. Travelers talk about their favorite places to visit, the services they use, and their overall impressions of the tourist industry. It gives you the lowdown on the dynamics of senior tourism. The tourist industry's best practices, market dynamics, and more significant trends can be better understood using secondary data compiled from published articles, papers, and internet sources. Scholarly discourse and industrial trends provide a broader framework within which researchers can explain their findings through synthesis and analysis of prior research.

3.3 Fuzzy Decision Support System Integration

A vital component of the research design is the incorporation of a state-of-the-art fuzzy decision support system (FDSS). It shows that the research is dedicated to using cutting-edge technology to tackle the complex issues of serving middle-aged and senior travelers. Central to this integration is the skillful application of fuzzy logic principles. These principles equip the FDSS to handle the complex dynamics of demographic variety, travel preferences, and other important aspects that shape the tourist industry. Fuzzy logic is an alternative to rigid binary logic systems that provide a more flexible and subtle basis for decision-making. Fuzzy logic allows for a more detailed portrayal of real-world complications by accommodating degrees of truth, unlike binary systems that function under tight limits of true or false. This adaptability is paramount for senior travel, as tastes and requirements can be unpredictable and changeable.

Let us assume that \(X\) is the input variables that indicate cultural sensitivity, accessibility concerns, travel preferences, and demographic profiles. \(Y\) stands for personalized tourist suggestions in the output variable. "\(\mu\)" is the membership function that denotes the level of truth for every input variable. Process the input variables and generate the output recommendations using the fuzzy logic method. By handling degrees of truth and capturing the many subtleties of demographic variety and travel preferences, the FDSS can traverse the complexity of the tourism landscape due to the integration of fuzzy logic principles. Equation (9), a mathematical expression, represents this break from conventional binary logic systems:

$$Y=f(X)$$
(9)

In this scenario, \(f\) takes data from middle-aged and senior travelers in the form of input variables X and uses fuzzy logic algorithms to produce Y, personalized recommendations for their vacation. The level of truth for each input variable is represented by the fuzzy logic algorithms using membership functions \(\mu\).

The FDSS is an advanced analytical engine that can handle large data sets with complex parameters, such as cultural sensitivity, accessibility concerns, travel preferences, and demographic diversity. Using fuzzy logic algorithms, the FDSS can simplify these complicated data sets into valuable insights. It allows those involved in the tourist business to better meet the needs of middle-aged and senior passengers. Navigating the inherent complexity of the tourism landscape is one of the FDSS's primary competencies. Travelers in the middle-aged and older age groups are a diversified demographic with a wide range of interests, socioeconomic status, and lifestyle variables. The FDSS deftly negotiates this variety, finding trends and patterns in the data to reveal new tastes and changing customer habits.

The FDSS is an advanced analytical engine that can handle massive data sets, including users' demographic information, travel preferences, accessibility concerns, and cultural sensitivity levels. It is possible to express it using the following equation:

$${\text{Y}}={\text{f}}\left({\upmu }_{{\text{X}}1 },{\upmu }_{{\text{X}}2},\dots ,{\upmu }_{{\text{Xn}}}\right)$$
(10)

Fuzzy logic techniques are used to transform the membership functions \({\mu }_{X1}, {\mu }_{X2},..., {\mu }_{Xn}\) for each input variable \({X}_{1}, {X}_{2},..., {X}_{n}\), and then to produce personalized tourist recommendations \(Y\). Discovering patterns and trends in the data to uncover growing preferences and developing consumer behaviors makes the FDSS adept at navigating the complex tourism scene. Fuzzy logic algorithms are used to examine the dynamic interplay between demographic characteristics and travel preferences and handle accessibility constraints and cultural sensitivity. This adaptable flexibility is shown through.

Essentially, incorporating the FDSS signifies a sea change in the perspective and provision of services to older populations by those involved in the tourism industry. With the help of fuzzy logic and advanced analytics, the FDSS allows stakeholders to ditch cookie–cutter methods and go for a more customized approach when creating tourist products. Ultimately, the FDSS acts as a spur to innovation in the tourist sector, encouraging the development of experiences that cater to the varied tastes and requirements of middle-aged and older tourists in a way that is both life-changing and incredibly rewarding.

3.4 Data Analysis

The research methodology is designed to gather and analyze data thoroughly to understand the target demographic's preferences, behaviors, and expectations regarding tourism experiences. It uses a mix of primary and secondary data-gathering techniques, chosen for their ability to systematically capture the nuanced viewpoints and experiences of the middle-aged and older tourist population. Engaging with middle-aged and senior travelers, the research uses primary data collection methods, such as surveys, interviews, and focus group discussions. Travelers talk about their favorite places to visit, the services they use, and their overall impressions of the tourist industry. It gives you the lowdown on the dynamics of senior tourism. The tourist industry's best practices, market dynamics, and more significant trends can be better understood using secondary data compiled from published articles, papers, and internet sources. Researchers can place their findings in the context of scholarly discourse and industrial trends by studying and synthesizing previous research.

Rigid examination of the gathered data utilizes state-of-the-art fuzzy logic algorithms designed to deal with the complexity and uncertainty inherent in real-world data. A more complex knowledge of the many elements impacting visitor behavior and preferences can be achieved through fuzzy logic, which allows academics to model and analyze the ambiguous and imprecise human decision-making processes. Researchers might find valuable suggestions for tourist product personalization through fuzzy logic analysis, which finds patterns, correlations, and concealed insights in the data set. The data analysis step lays the groundwork for the personalization technique for tourism experiences for middle-aged and older travelers. Researchers can improve the tourist experience for everyone by studying the target demographic to find out their likes, dislikes, and problems. Travel itineraries tailored to the specific needs of elderly tourists may be among the suggestions made, along with accessibility upgrades, cultural immersion events, and other specialist services.

Overall, the research methodology's data collecting and analysis phase takes a multi-pronged approach, mining primary and secondary sources of information and cutting-edge fuzzy logic techniques to reveal hidden details about senior tourism. Using these findings, researchers can create tourist products and services catering to middle-aged and older tourists' different tastes and needs, making their trips more enjoyable.

4 Development of METP–FDSS Framework

System development and implementation constitute a critical step in the research endeavor, building upon the conceptual framework and data analysis to realize the middle-aged and elderly tourism products based on the fuzzy decision support system framework. This advanced framework is ready to be a dynamic decision-support tool, providing all people involved in the tourist industry with helpful advice and direction. The system development process aims to include complex factors and detailed insights into the METP–FDSS framework, expanding upon the conceptual framework's core pillars. For this reason, it is essential to thoroughly research cultural sensitivities, accessibility needs, travel preferences, and demographic trends to guarantee that the framework can meet the varied expectations of middle-aged and older travelers. Figure 1 depicts the METP–FDSS model's architecture.

Fig. 1
figure 1

System structure of METP–FDSS model

Full size image

4.1 User Profiling

An integral part of the METP–FDSS system, user profiling aims to improve the relevance and customization of travel suggestions for middle-aged and older travelers. Data on demographics, preferences, prior travel habits, and special needs are just a few aspects that the user profile module gathers and combines. The system's ability to personalize suggestions to meet the interests and limitations of individual travelers depends on this data, which is why it is so important. The METP–FDSS can divide tourists into several groups according to their age, past trips, favorite activities, spending limit, and accessibility needs using detailed user profiles. The provision of tailored recommendations and the enhancement of user happiness are both supported by these profiles.

An assortment of structured and unstructured data sources, such as online reviews, sentiment analysis on social media, and past travel habits, are mined for valuable insights by the METP–FDSS using cutting-edge data analytics tools. The system can provide better suggestions by integrating quantitative data analysis with qualitative user feedback, which allows it to discover hidden trends and patterns. The METP–FDSS framework relies heavily on user profiling and destination analytics modules to improve the user experience and satisfaction. These modules allow travelers to make informed decisions and embark on unforgettable adventures tailored to their preferences and requirements by utilizing advanced algorithms and real-time data processing capabilities.

4.2 Algorithm Design and Implementation

The foundation of the middle-aged and elderly tourism products based on a fuzzy decision support system framework is algorithmic design and implementation. It ushered in a world of complex algorithms and advanced computational models that could navigate the intricacies of senior tourism with unmatched accuracy and understanding.

4.2.1 Fuzzy Logic Principles

Fuzzy logic principles, a mathematical framework that allows the depiction of uncertainty and imprecision in decision-making processes, are central to the algorithmic design of the METP–FDSS system. The ability to attribute propositions with varying degrees of truth sets fuzzy logic apart from conventional binary logic. Fuzzy sets, membership functions, linguistic variables, and fuzzy rules are the main components of fuzzy logic. There are two ways to classify a tourist's age in conventional binary logic: "middle-aged" and "elderly." Fuzzy logic enables a representation with subtleties. For example, the degree of an undefined variable "Age" can be anywhere from "0.7 middle-aged" to "0.3 elderly," which captures the slow shift between groups.

Fuzzy logic can account for the fact that middle-aged and elderly tourists have different levels of interest in outdoor activities for senior tourism. According to the rules of classical binary logic, a traveler's enthusiasm for outdoor pursuits might be characterized as "high" or "low." However, the desire for outside activities can be more nuancedly described via fuzzy logic. Take the hypothetical "Outdoor Activity Preference" fuzzy variable representing a middle-aged traveler as an example. Rather than a simple yes/no, this variable can take on numeric values, such as "0.8 high" and "0.2 low," suggesting a strong preference for outside activities with room for indoor alternatives. Similarly, a senior traveler's "Outdoor Activity Preference" variable could contain values, such as "0.4 high" and "0.6 low," indicating a moderate interest in outdoor activities but a preference for more laid-back indoor alternatives. The depiction of fuzzy logic in the context of elder tourism is shown in Table 2.

Table 2 Fuzzy logic representation of senior tourism variables
Full size table

Table 2 shows the degrees of membership in particular categories or preferences for middle-aged and older travelers for each variable relevant to senior tourism, rendered with fuzzy logic. These visuals show how decision support systems may learn more about middle-aged and senior travelers' tastes and traits using fuzzy logic and provide more personalized suggestions according to that knowledge. Due to this detailed portrayal, the decision-support system can now personalize its tourism suggestions for middle-aged and older travelers according to their varied levels of interest in outdoor activities. Recognizing the range of preferences within these demographic groupings allows the system to tailor recommendations to meet each traveler's specific needs and preferences.

4.2.2 Fuzzy Inference Systems

The METP–FDSS architecture is based on fuzzy inference systems (FIS), which provide a systematic way to incorporate human expertise and heuristics into computer models. The four main parts of FIS are fuzzification, assessment of fuzzy rules, aggregation, and defuzzification. Processing input data, evaluating fuzzy rules, consolidating outcomes, and producing exact output values are all accomplished by these parts working in perfect harmony. Consider a situation where the FIS assesses the preferences of travelers. Assume a traveler displays a "nature preference" degree of "0.4" and a "cultural preference" degree of "0.8." The FIS produces a clean output by efficiently processing and assessing the degrees of membership of various fuzzy inputs. The greater membership degree here suggests a stronger preference for cultural activities, so the algorithm recommends a tourist activity that fits that Preference.

The process of fuzzyification entails converting clean input data into fuzzy sets by giving linguistic variables membership degrees. As an example, considering that "age" is 45 years, it is possible to use fuzzy sets, such as "middle-aged" with a membership degree of "0.7" and "elderly" with a degree of "0.3," which would capture the seamless transition between the two categories. An evaluation of fuzzy rules involves gazing at a collection of already created rules and how they link input variables to output variables. The rules help the system make decisions by encapsulating subject knowledge and skills. For example, a rule could be as follows: suggest moderately energetic tourist activities IF "age" is middle-aged AND "health condition" is good.

The METP–FDSS paradigm revolves around the fuzzy inference engine (Fig. 2), which systematically incorporates human knowledge and heuristics into computer models. The four main parts of FIS are fuzzification, aggregation, defuzzification, and fuzzy rule evaluation. Input data are processed, fuzzy rules are evaluated, results are aggregated, and crisp output values, such as personalized tourist recommendations, are generated by these parts working in tandem.

Fig. 2
figure 2

Fuzzy inference engine in the METP–FDSS framework

Full size image

Aggregation is merging the results of different rules to get a more complete outcome. This method considers each rule's relative relevance and significance in the decision-making process and synthesizes their unique contributions. Defuzzification turns the combined fuzzy results into a clear and practical suggestion. This last stage guarantees that the system aids tourist sector players in making informed decisions and developing products by providing them with clear and intelligible guidance. Including FIS into the METP–FDSS architecture provides stakeholders with a powerful decision support system that can handle complicated inputs, assess fuzzy rules, and provide personalized suggestions that align with the tastes and requirements of middle-aged and older travelers.

4.2.3 Membership Functions

Fuzzy logic systems rely heavily on membership functions, which allow us to measure the degree of integrity or membership associated with linguistic variables in fuzzy sets. By connecting input variables to fuzzy sets, these functions make it possible to describe concepts that are either unclear or imprecise quantitatively. Membership functions allow the system to understand language and determine the degree to which an input variable is part of a specific fuzzy set by outlining the borders of such sets. Fuzzy logic systems rely on membership functions. \({\mu }_{A}(x)\) to measure the degree of truthfulness or membership associated with linguistic variables x in fuzzy sets A. These functions facilitate the quantitative representation of vague or unclear concepts by mediating between input variables and fuzzy sets. The mathematical concept of a membership function, denoted as \({\mu }_{A}(x)\), assigns a value between \(0 {\text{and}} 1\) to each element x in the discourse universe \(X\), reflecting the extent to which \(x\) is a member of the fuzzy set \(A\).

Several membership functions are explored, each designed to capture different aspects of language variables and account for different domain-specific uncertainty levels. Gaussian membership functions are essential in the METP–FDSS framework for capturing variables with complicated and non-linear interactions. These relationships are present in middle-aged and senior visitors' varied tastes and characteristics. Gaussian membership functions are ideal for variables with unclear or overlapping borders because their bell-shaped curves provide an easy transition between membership and non-membership. Equation (11) provides the mathematical expression for a Gaussian membership function \(\mu Gaussian\):

$$f(x)={e}^{-\frac{{\left(x-\mu \right)}^{2}}{2{\sigma }^{2}}}$$
(11)

The mean or center of the curve, denoted by \(\mu\), indicates the point of highest membership. In contrast, the breadth of the curve, controlled by \(\sigma\), determines the dispersion or variability of the membership function. Travel satisfaction levels, which can show complex and non-linear relationships impacted by destination attributes, level of service, and personal preferences, can be fitted with Gaussian membership functions within the METP–FDSS framework. The METP–FDSS framework can capture the complex and ever-changing character of middle-aged and older visitors' trip satisfaction using Gaussian membership functions. The inherent uncertainty and complexity of visitor experiences can be accommodated using Gaussian functions, which offer a smooth transition and can thus express tiny variations in satisfaction levels.

Moreover, the framework can tailor recommendations and insights to the diverse needs and preferences of middle-aged and elderly travelers by adapting Gaussian membership functions to capture the various levels of satisfaction experienced by multiple visitor segments. Finally, the METP–FDSS framework can use Gaussian membership functions to represent and analyze complex variables, such as travel satisfaction levels. It will help create tailored and meaningful tourist goods and services for senior and middle-aged travelers.

4.2.4 Fuzzy Rule Base

An integral part of the METP–FDSS architecture, the fuzzy rule base offers a systematic way to encode domain-specific heuristics and expert knowledge into practical suggestions adapted to the complex requirements of middle-aged and older travelers. The fuzzy rule base is a set of IF–THEN rules describing the connections between input and output variables about senior tourism. The decision-making process inside the METP–FDSS framework is guided by these guidelines, which outline the proper interpretation of incoming data to provide relevant suggestions.

Incorporating professional knowledge about the habits and tastes of middle-aged and senior travelers, this rule recognizes that people in this age group often enjoy cultural activities. The METP–FDSS framework uses fuzzy logic to classify input data about age and travel preferences into "middle-aged" and "cultural." For instance, the fuzzy rule would confidently suggest cultural heritage tours to tourists who fall into the middle-aged' category with a high degree of membership (e.g., 0.8) and strongly prefer cultural activities (e.g., 0.7). On the other hand, the advice might change depending on the fuzzy logic assessment if the tourist tends to have different travel preferences and is closer to the 'elderly' age group.

Many other rules can be included in the METP–FDSS framework's fuzzy rule base to handle different situations and preferences related to senior tourism. Fuzzy rules can be used to suggest outdoor activities to nature-loving tourists, spa and wellness pursuits to relaxation-seeking tourists, or gastronomic adventures to foodies. For example, consider this fuzzy rule: Suggestions for cultural heritage tours should be made if the age is in the middle years and the type of travel preferred is artistic. The rule states that the input variables 'age' and 'travel preference' should be considered, with the recommended tourist activity 'cultural heritage tours' as the output variable. Based on the framework of the fuzzy decision support system, Table 3 shows several fuzzy rules specific to middle-aged and elderly tourist products.

Table 3 Fuzzy rules specific to middle-aged and elderly tourist products
Full size table

The METP–FDSS system can use these fuzzy criteria as a starting point for making suggestions tailored to the interests and demographics of middle-aged and senior travellers. Every rule represents a possible outcome when particular criteria are satisfied, and each corresponds to a recommendation that is made according to the tastes of the intended audience. The fuzzy rule base allows the METP–FDSS framework to produce individualized suggestions that cater to middle-aged and senior travelers' varied tastes and requirements by encapsulating expert knowledge and domain-specific insights. The framework improves senior tourism by allowing for the precise application of IF–THEN criteria, which in turn allow for the development of personalized tourist experiences that truly connect with the intended audience and boost happiness and participation.

4.2.5 Iterative Improvement and Validation

Central to the algorithmic design of the METP–FDSS architecture is the iterative improvement and validation phase, which embodies a dynamic and iterative strategy to improve accuracy and reliability continuously. This part works by iteratively testing algorithms with benchmark data sets and real-world scenarios, then refining them based on stakeholder feedback and actual data. The METP–FDSS algorithms are carefully examined and fine-tuned as part of the improvement process. Crucial to the optimization of algorithmic parameters is stakeholder participation, which provides insightful input. The METP–FDSS is updated to meet middle-aged and senior tourists' changing demands and preferences through this interactive modification in the following equation:

$${A}_{{\text{new}}}=f({A}_{\mathrm{old }},\mathrm{ Stakeholder\, Feedback},{\text{Real}}-\mathrm{world\, Data})$$
(12)

\({\text{Stakeholder}}\), \(A\_{\text{old}}\), and \(A\_{\text{new}}\) stand for the current and improved algorithms, respectively. Stakeholders' qualitative views and recommendations are encapsulated in feedback. The term "\({\text{Real}}-{\text{world}} {\text{data}}\)" refers to information that is constantly updated based on actual situations. If the METP–FDSS is to be trustworthy and resilient, validation is an essential phase. Testing the system extensively against benchmark data sets and real-world scenarios is integral to this process. Further refining is applied to resolve deviations or inaccuracies found when the METP–FDSS algorithms are tested using established metrics. The validation procedure renders a quantitative evaluation of the system's functionality and conformity to predetermined standards. The METP–FDSS is designed to fully respond to the unique needs of middle-aged and elderly travellers through an iterative process of refinement and validation. A continuous feedback loop that includes quantitative and qualitative features supports the system's optimization and evolution over time. It makes it a trustworthy decision-support tool in the ever-changing world of senior tourism.

The METP–FDSS framework goes above and beyond conventional decision-making models by skillfully applying fuzzy logic principles and advanced computational models. As a result, it provides tourism industry stakeholders with unmatched insights and suggestions specifically designed to meet the complex needs and preferences of middle-aged and elderly travelers. Fuzzy logic allows the framework to deftly traverse the complex world of senior tourism, opening the door to a new age of tailored and life-altering vacations.

4.3 User Interface and Accessibility

An intuitive, user-friendly interface that complements the complex mathematical design has been the primary focus of the METP–FDSS framework's development. Stakeholders and the complex decision-making [28] procedures housed in the system are connected through this interface. The development of this product is guided by a user-friendly design philosophy that recognizes the wide variety of technical abilities and knowledge held by the end users. Stakeholders may move about the framework with simplicity and efficacy because the interface's painstaking engineering allows smooth interactions. Users can fully utilize the METP–FDSS model without facing excessive complexity or obstacles to entrance due to intuitive design components and simple navigation pathways. Prioritizing the user experience is crucial because it allows stakeholders with varying technical knowledge to get valuable insights and suggestions from the system.

The design philosophy of the framework is permeated with accessibility considerations. The significance of inclusion and universal access is acknowledged, and users with varying technology literacy levels are given special attention. The interface is designed to be user-friendly and accessible to people with different levels of technical knowledge. There is an effort to improve usability and reduce the learning curve for users by incorporating clear instructions, visual clues, and user-friendly layouts into the system. In addition, the interface is thoroughly tested and validated to guarantee its efficacy for various user demographics and accessibility needs. Iterative upgrades and modifications are made possible by feedback mechanisms, which gather user input and enhance accessibility and usability over time.

Enabling stakeholders to navigate senior tourism's complexity confidently, the user interface ultimately unlocks the potential of the METP–FDSS framework by promoting informed decision-making. The framework's overarching goal is to promote inclusivity and collaboration in the tourist industry by democratizing access to valuable insights and recommendations through a strategy that prioritizes user experience and accessibility.

4.4 Stakeholder Engagement and Collaboration

An active invitation is extended to industry players to actively contribute their skills and viewpoints to the ongoing growth of the framework through stakeholder engagement, which is not a passive process. Key stakeholders must be actively involved and work together as the METP–FDSS framework develops if it is to be effectively implemented. The framework highlights the importance of establishing genuine partnerships and encouraging open communication among the many tourist sector stakeholders, including destination managers, tour operators, and hotel providers. The METP–FDSS model provides a forum for stakeholders to share their thoughts, feelings, and recommendations via focus groups, feedback sessions, and collaborative workshops.

All stakeholders' needs and views will be carefully considered throughout the validation and improvement of the framework because of the open and participatory nature of the engagement approach. The METP–FDSS framework gains a wealth of information and experiences by including a diverse range of stakeholders, making it more effective and relevant in solving real-world problems. In addition, stakeholders are more likely to trust, buy in, and develop a sense of ownership when actively involved in the process. The framework fosters a collaborative ecosystem by incorporating stakeholders into the co-creation process. It makes stakeholders feel that their investment in the METP–FDSS initiative's success and sustainability is essential.

The framework may be continuously improved and optimized in response to changing industry dynamics and new priorities, since feedback loops are generated through an iterative stakeholder involvement process. The METP–FDSS framework can adapt to stakeholders' changing demands and preferences in the senior tourism industry because of its iterative methodology. Stakeholder participation and collaboration are crucial for the METP–FDSS framework to be adopted and implemented successfully. It will promote a culture of collaboration, innovation, and collective accountability in the tourism industry. The framework aims to improve senior tourism programs' general viability and sustainability through continuous discussion and partnership, which will promote innovation and catalyze positive change.

4.5 Refinement and Validation

A systematic approach to continuous refinement and validation is necessary to integrate fuzzy logic concepts inside the METP–FDSS framework. This methodology underpins the framework's evolution and effectiveness in meeting senior tourism's complex needs. The framework is improved and optimized continuously during the iterative refinement phase based on stakeholder feedback and real-world insights. The developers can increase the framework's performance and flexibility by iteratively fine-tuning algorithms, adjusting parameters, and incorporating new approaches. As the framework is applied in various tourism contexts, stakeholder input acts as a compass, offering priceless insights into the practical difficulties and possibilities that arise.

In addition, data gathered from operational deployments and pilot studies carried out in real tourist situations help the refinement process. Developers can better understand the framework's strengths and weaknesses by evaluating data trends, finding patterns, and inspecting performance indicators. This knowledge then informs strategic decisions to enhance the framework's overall efficacy. Iterative validation is essential for validating the METP–FDSS architecture in various operational scenarios to ensure its reliability and resilience. Developers can evaluate the framework's performance in different environments and put its capabilities to the test by running it through extensive tests against benchmark data sets and simulated scenarios. The METP–FDSS framework relies on iterative refinement and validation as its quality assurance pillars; these pillars propel innovation and continual development in decision support systems for senior tourists. An iterative learning and adaption culture maintains the framework's ability to respond to changing trends, user demands, and industry landscapes. It ensures that the framework will continue shaping the future of senior tourist experiences.

The development and execution of the METP–FDSS framework essentially demonstrates the research's dedication to creativity, cooperation, and stakeholder engagement. The framework unlocks new frontiers of personalized and inclusive travel experiences for middle-aged and elderly travellers using sophisticated computational models and fuzzy logic principles. It signals a new era of data-driven choices within senior tourism.

5 Evaluation and Analysis

In the study's experimental analysis, the performance of the METP–FDSS framework is evaluated thoroughly. Validation and systematic testing against Kaggle benchmark data sets [29] assessing personalization accuracy, adaptability, flexibility, recall, user satisfaction, engagement metrics, coverage, and conversion rate. The METP–FDSS framework is evaluated with other fuzzy-based models such as the Mamdani fuzzy inference system (MFIS), sugeno fuzzy inference system (SFIS), and fuzzy cognitive maps (FCM) to get a feel for how well it handles the complex needs of middle-aged and elderly tourists in the hospitality sector.

5.1 Data Set

The extensive travel data [29] included in this experimentation includes trip specifics, such as location, departure and arrival dates, length, traveller demographics (name, age, gender, nationality), lodging type and cost, mode of transportation and expenses, and more. The diverse trips taken by travellers provide insights into travel habits, preferences, and behaviors across demographics and destinations. The data set is a goldmine for travel trend analysis, marketing strategy development, and segmentation of travel service demand due to the columns that specify a trip ID, destination, dates, duration, traveller details, lodging, and transportation specifics. Accuracy metric helps measure the system's ability to generate precise and reliable recommendations aligned with the target demographic's preferences, ensuring high-quality tourism product offerings. Robustness analysis assesses the system's resilience and consistent performance under diverse scenarios and inputs, crucial for handling the inherent uncertainties and complexities involved in catering to the middle-aged and elderly traveler segment.

5.2 Accuracy Analysis

A comparison of the accuracy rates of various models, as shown in Fig. 3, indicates that the MTEP–FDSS model outperforms the others. The MTEP–FDSS outperforms the FCM, SFIS, and MFIS models in terms of accuracy over 10 months. The MTEP–FDSS outperforms the other models, which have an accuracy rate ranging from 72 to 82%, with an average performance of 88%. This trend demonstrates the MTEP–FDSS's ability to generate accurate travel recommendations consistently across various periods. In addition, the MTEP–FDSS shows very stable accuracy rates from month to month, which is a sign of its reliability and consistency. On the other hand, other models exhibit a more comprehensive range of accuracy rates, which may indicate that they are less reliable predictors or more vulnerable to data fluctuations. Stakeholders in the tourism industry widely use the MTEP–FDSS model to improve customer satisfaction and engagement due to its consistently high accuracy rates, which prove its effectiveness in providing accurate and reliable travel recommendations.

Fig. 3
figure 3

Accuracy rate of the proposed METP–FDSS and other fuzzy-based models

Full size image

5.3 User Satisfaction Analysis

Figure 4 shows the user satisfaction rate over ten months, which indicates that the MTEP–FDSS model is better than the FCM, SFIS, and MFIS models. It means that the MTEP–FDSS platform has higher levels of user satisfaction. The MTEP–FDSS model has consistently met user expectations and delivered valuable insights and recommendations across all ten months, as indicated by consistently high user satisfaction scores. It suggests that the MTEP–FDSS platform is easy to use, dependable, and meets the needs and preferences of its users. Improving user happiness is a breeze with the help of the MTEP–FDSS model. Its intuitive design and user-friendly interface make it easy for stakeholders to use, and the fact that it gives them accurate and relevant suggestions makes them happier. Models such as FCM, SFIS, and MFIS perform worse than this because of their less user-friendly interfaces, inaccurate results, and poor design. Nevertheless, the satisfaction scores of the MTEP–FDSS model have been steadily rising over the last 10 months, suggesting that the model is constantly being optimized and improved according to user feedback and real-world data. By continuously improving the platform based on user feedback, this study can keep it tailored to their needs and preferences, ultimately leading to higher satisfaction.

Fig. 4
figure 4

User satisfaction rate of the proposed METP–FDSS and other fuzzy-based models

Full size image

5.4 Robustness Analysis

The MTEP–FDSS model outperforms the FCM, SFIS, and MFIS models in managing various situations and maintaining consistent performance, as shown in the robustness score across six weeks (Fig. 5). The MTEP–FDSS outperforms its competitors in terms of robustness week after week. Due to its advanced algorithmic design and application of fuzzy logic principles, the MTEP–FDSS model provides stakeholders in the tourism industry with a robust decision support system. Reliable recommendations and insights are delivered as they deftly deal with uncertain and dynamic conditions. The model's capacity to reliably provide insights is indicated by its robustness scores, which range from 86 to 96 during the observation period. Stakeholders can better make educated decisions even when faced with unknowns due to their increased robustness. Stakeholders can have faith in the model's reliability and validity to provide reliable and precise recommendations, which improves decision-making and boosts the efficacy and efficiency of tourist operations.

Fig. 5
figure 5

Robustness score (%) of the METP–FDSS and other comparative models

Full size image

5.5 Repeat Visitation Analysis

Figure 6 compares the MTEP–FDSS model to the FCM, SFIS, and MFIS models in terms of the rate of repeat visitors over ten months. The MTEP–FDSS successfully encourages visitor loyalty and engagement, as evidenced by its consistently higher repeat visitor rates during the observation period. Compared to other models such as FCM, SFIS, and MFIS, the MTEP–FDSS model achieves a much higher initial rate of repeat visitors (75%). This pattern persists in the following months, with the MTEP–FDSS continuing to have higher rates of repeat visitors than its competitors. Because it can customize tourism experiences according to individual preferences and behaviours, the MTEP–FDSS model successfully attracts repeated visitors. The model finds and suggests experiences that resonate with visitors, encouraging a feeling of contentment and loyalty, by utilizing fuzzy logic principles and sophisticated algorithms. The MTEP–FDSS model can increase client retention and long-term worth for tourism stakeholders due to its higher associated repeat visitor rates. Repeat customers are invaluable to the tourism industry because they bring in more money and spread the word about the brand. It shows how critical data-driven insights and personalized recommendations are. Stakeholders can maximize customer lifetime value and improve visitor experiences with the help of the MTEP–FDSS model, which encourages the cultivation of meaningful relationships with visitors.

Fig. 6
figure 6

Repeat Visitation rate (%) of the METP–FDSS and other fuzzy-based models

Full size image

5.6 Conversion Rate Analysis

Figure 7 shows the conversion rates of marketing initiatives implemented over ten months using various decision support models. Compared to the MFIS, SFIS, and FCM models, the MTEP–FDSS model's continuously superior conversion rates show how effective it is at optimizing marketing techniques. Despite outperforming all other models, MTEP–FDSS obtains a conversion rate of 0.25 in the first month. MTEP–FDSS keeps its increased conversion rates month after month, continuing this trend. By the ninth month, MTEP–FDSS continues outperforming other models with a noteworthy conversion rate of 0.23. The comprehensive analytical skills and robust algorithmic framework of MTEP–FDSS are the reasons for its exceptional performance in increasing conversion rates. The algorithm finds and prioritizes marketing strategies that appeal to target audiences, optimizing conversion opportunities by leveraging fuzzy logic principles and advanced data analysis tools. The impressive conversion rates produced by MTEP–FDSS highlight its ability to engage customers and deliver real business results for those involved in the travel industry. Marketers can engage and convert potential tourists into buyers by precisely anticipating their behavior and preferences using the model. Due to data-driven insights and sophisticated analytics, research shows that MTEP–FDSS is useful as a decision-support tool for the tourist industry's marketing strategy optimization efforts.

Fig. 7
figure 7

Conversion analysis of the METP–FDSS and other fuzzy-based models

Full size image

5.7 Coverage Analysis

Coverage of customized travel services offered by various decision support models over ten months is shown in Fig. 8. Across all months; the MTEP–FDSS model achieves better coverage than the MFIS, SFIS, and FCM models. MTEP–FDSS has a first-month coverage rate of 85% compared to previous models. Throughout the study, MTEP–FDSS maintained its lead in coverage rates, outperforming its competitors. The coverage rate of MTEP–FDSS approaches 92% by the ninth month, while other models fall behind. The advanced analytics and fuzzy logic techniques used in MTEP–FDSS's algorithmic design are the reasons for its higher coverage. The program efficiently sifts through several data sets in search of middle-aged and older travellers' preferences and needs and then suggests individualized travel options to fulfill those needs. The MTEP–FDSS can accommodate various travel demands and preferences due to its high coverage rate, making the experience more enjoyable. Customers are satisfied and loyal because of the comprehensive and individualized travel services it provides. The study recommends more investigation into improving the model's algorithms and enhancing its capacity to transform the delivery of travel services in the tourism sector.

Fig. 8
figure 8

Coverage rate (%) analysis of the METP–FDSS and other fuzzy-based models

Full size image

5.8 Personalization Accuracy Analysis

Figure 9 shows the adaptability rate, which shows how well each model in the METP–FDSS architecture reacts to changes over time. Here, "adaptability" means how well the model can change in response to new information, user tastes, or market trends. It continues outperforming FCM, SFIS, and MFIS regarding flexibility, suggesting it can better handle changing conditions. For example, compared to FCM (75), SFIS (70), and MFIS (62) in Week 1, MTEP–FDSS begins with an adaptation score of 88—the tendency of MTEP–FDSS to continuously get the best adaptation scores persists throughout the observation period. Several variables contribute to MTEP–FDSS's remarkable adaptability. Perhaps it uses more advanced algorithms that swiftly take fresh information into account and modify its suggestions appropriately. It may also use dynamic decision-making procedures or sophisticated machine learning methods to adapt to new conditions. As a result of their poorer adaptability scores, models such as FCM, SFIS, and MFIS may have difficulty adjusting to unique circumstances. Possible causes include insufficient real-time feedback methods, weak data processing capabilities, or algorithmic restrictions. Stakeholders in the tourism industry can make informed decisions in real-time and efficiently handle challenging scenarios because of its adaptability, which enhances its utility in dynamic environments.

Fig. 9
figure 9

Adaptability rate (%) analysis of the METP–FDSS and comparative models

Full size image

The experimental analysis phase of the research thoroughly assesses how well the METP–FDSS system works. Accuracy, precision, recall, user satisfaction, engagement metrics, coverage, adaptability, flexibility, robustness, and personalization accuracy were assessed and verified using benchmark data sets in the METP–FDSS, a fuzzy-based model. Models such as fuzzy cognitive maps (FCM), Mamdani fuzzy inference system (MFIS), and sugeno fuzzy inference system (SFIS) are used to compare the model's performance. With better accuracy rates during 10 months, the MTEP–FDSS model consistently beats other models. More user satisfaction is a result of its precise suggestions and user-friendly design. A trustworthy decision-support system, the model resists changes and unknowns in the tourist industry. Customer retention, engagement, and marketing strategy optimization could be driven by the model's outperformance in coverage, flexibility, conversion rate, and return visitors. The findings generally confirm that the MTEP–FDSS framework is valuable and helpful in improving tourist decision-making and customer experiences.

6 Conclusion

This study highlights the importance of the METP–FDSS framework for improving decision-making and creating customized tourism goods for middle-aged and elderly travelers. The main results show that compared to other fuzzy-based models, the METP–FDSS always does better in terms of coverage, accuracy, user happiness, robustness, conversion rate, and rate of return visitors. These results demonstrate that the framework effectively produces reliable travel suggestions, encourages repeat visits, improves advertising campaigns, and meets various travel requirements. This research aims to apply the METP–FDSS framework to enhance customer engagement and satisfaction while designing tourism products for middle-aged and senior travellers. It proves that data-driven decision-support tools can handle complicated problems in the industry. Contributing to tourist product creation and proving the worth of data-driven decision support systems, the framework aids stakeholders in making educated decisions, optimizing resource allocation, and improving operational efficiency. Thus the METP–FDSS system ensures 92% coverage rate and 96% of robustness value compared to the other methods.

6.1 Limitations and Future Directions

The reliability and generalizability of the research may have been affected by limitations that must be acknowledged. The use of specific data sets and the possibility of bias in data collecting are two examples. Research in the future might investigate ways to improve decision support systems in the tourist industry by combining real-time data with predictive analytics, advanced machine learning methods. Ultimately, this study paves the way for advancement in decision support systems and tourist product creation. Tailoring tourism research and industry practices to the evolving needs and preferences of middle-aged and elderly travelers can drive long-term sustainability within the sector.