Encyclopedia of Big Data

Living Edition
| Editors: Laurie A. Schintler, Connie L. McNeely

Behavioral Analytics

  • Lourdes S. MartinezEmail author
Living reference work entry
DOI: https://doi.org/10.1007/978-3-319-32001-4_18-1

Keywords

Game Development Behavioral Analytic Data Mining Technique Business Analytic Game Industry 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Behavioral analytics can be conceptualized as a process involving the analysis of large datasets comprised of behavioral data in order to extract behavioral insights. This definition encompasses three goals of behavioral analytics intended to generate behavioral insights for the purposes of improving organizational performance and decision-making as well as increasing understanding of users. Coinciding with the rise of big data and the development of data mining techniques, a variety of fields stand to benefit from the emergence of behavioral analytics and its implications. Although there exists some controversy regarding the use of behavioral analytics, it has much to offer organizations and businesses that are willing to explore its integration into their models.

Definition

The concept of behavioral analytics has been defined by Montibeller and Durbach as an analytical process of extracting behavioral insights from datasets containing behavioral data. This definition is derived from previous conceptualizations of the broader overarching idea of business analytics put forth by Davenport and Harris as well as Kohavi and colleagues. Business analytics in turn is a subarea within business intelligence and described by Negash and Gray as systems that integrate data processes with analytics tools to demonstrate insights relevant to business planners and decision-makers. According to Montibeller and Durbach, behavioral analytics differs from traditional descriptive analysis of behavioral data by focusing analyses on driving action and improving decision-making among individuals and organizations. The purpose of this process is threefold. First, behavioral analytics facilitates the detection of users’ behavior, judgments, and choices. For example, a health website that tracks the click-through behavior, views, and downloads of its visitors may offer an opportunity to personalize user experience based on profiles of different types of visitors.

Second, behavioral analytics leverages findings from these behavioral patterns to inform decision-making at the organizational level and improve performance. If personalizing the visitor experience to a health website reveals a mismatch between certain users and the content provided on the website’s navigation menu, the website may alter the items on its navigation menu to direct this group of users to relevant content in a more efficient manner. Lastly, behavioral analytics informs decision-making at the individual level by improving judgments and choices of users. A health website that is personalized to unique health characteristics and demographics of visitors may help users fulfill their informational needs so that they can apply the information to improve decisions they make about their health.

Applications

According to Kokel and colleagues, the largest behavioral databases can be found at Internet technology companies such as Google as well as online gaming communities. The sheer size of these datasets is giving rise to new methods, such as data visualization, for behavioral analytics. Fox and Hendler note the opportunity in implementing data visualization as a tool for exploratory research and argue for a need to create a greater role for it in the process of scientific discovery. For example, Carneiro and Mylonakis explain how Google Flu relies on data visualization tools to predict outbreaks of influenza by tracking online search behavior and comparing it to geographical data. Similarly, Mitchell notes how Google Maps analyzes traffic patterns through data provided via real-time cell phone location to provide recommendations for travel directions. In the realm of social media, Bollen and colleagues have also demonstrated how analysis of Twitter feeds can be used to predict public sentiments.

According to Jou, the value of behavioral analytics has perhaps been most notably observed in the area of commercial marketing. The consumer marketing space has borne witness to the progress made through extracting actionable and profitable insights from user behavioral data. For example, between recommendation search engines for Amazon and teams of data scientists for LinkedIn, behavioral analytics has allowed these companies to transform their plethora of user data into increased profits. Similarly, advertising efforts have turned toward the use of behavioral analytics to glean further insights into consumer behavior. Yamaguchi discusses several tools on which digital marketers rely that go beyond examining data from site traffic.

Nagaitis notes observations that are consistent with Jou’s view of behavioral analytics’ impact on marketing. According to Nagaitis, in the absence of face-to-face communication, behavioral analytics allows commercial marketers to examine e-consumers through additional lenses apart from the traditional demographic and traffic tracking. In approaching the selling process from a relationship standpoint, behavioral analytics uses data collected via web-based behavior to increase understanding of consumer motivations and goals, and fulfill their needs. Examples of these sources of data include keyword searchers, navigation paths, and click-through patterns. By inputting data from these sources into machine learning algorithms, computational social scientists are able to map human factors of consumer behavior as it unfolds during purchases. In addition, behavioral analytics can use web-based behaviors of consumers as proxies for cues typically conveyed through in-person face-to-face communication. Previous research suggests that web-based dialogs can capture rich data pointing toward behavioral cues, the analysis of which can yield highly accurate predictions comparable to data collected during face-to-face interactions. The significance of this ability to capture communication cues is reflected in marketers increased ability to speak to their consumers with greater personalization that enhances the consumer experience.

Behavioral analytics has also enjoyed increasingly widespread application in game development. El-Nasr and colleagues discuss the growing significance of assessing and uncovering insights related to player behavior, both of which have emerged as essential goals for the game industry and catapulted behavioral analytics into a central role with commercial and academic implications for game development. A combination of evolving mobile device technology and shifting business models that focus on game distribution via online platforms has created a situation for behavioral analytics to make important contributions toward building profitable businesses.

Increasingly available data on user behavior has given rise to the use of behavioral analytic approaches to guide game development. Fields and Cotton note the premium placed in this industry on data mining techniques that decrease behavioral datasets in complexity while extracting knowledge that can drive game development. However, determining cutting-edge methods in behavioral analytics within the game industry is a challenge due to reluctance on the part of various organizations to share analytic methods. Drachen and colleagues observe a difficulty in assessing both data and analytical methods applied to data analysis in this area due to a perception that these approaches represent a form of intellectual property. Sifa further notes that to the extent that data mining, behavioral analytics, and the insights derived from these approaches provide a competitive advantage over rival organizations in an industry that already exhibits fierce competition in the entertainment landscape, organizations will not be motivated to share knowledge about these methods.

Another area receiving attention for its application of behavioral analytics is business management. Noting that while much interest in applying behavioral analytics has focused on modeling and predicting consumer experiences, Géczy and colleagues observe a potential for applying these techniques to improve employee usability of internal systems. More specifically, Géczy and colleagues describe the use of behavioral analytics as a critical first step to user-oriented management of organizational information systems through identification of relevant user characteristics. Through behavioral analytics, organizations can observe characteristics of usability and interaction with information systems and identify patterns of resource underutilization. These patterns are important in providing implications for designing streamlined and efficient user-oriented processes and services. Behavioral analytics can also offer prospects for increasing personalization during the user experience by drawing from user information provided in user profiles. These profiles contain information about how the user interacts with the system, and the system can accordingly adjust based on clustering of users.

Despite advances made in behavioral analytics within the commercial marketing and game industries, several areas are ripe with opportunities for integrating behavioral analytics to improve performance and decision-making practices. One area that has not yet reached its full potential for capitalizing on the use of behavioral analytics is security. Although Brown reports on exploration in the use of behavioral analytics to track cross-border smuggling activity in the United Kingdom through vehicle movement, the application of these techniques under the broader umbrella of security remains understudied. Along these lines and in the context of an enormous amount of available data, Jou discusses the possibilities for implementing behavioral analytics techniques to identify insider threats posed by individuals within an organization. Inputting data from a variety of sources into behavioral analytics platforms can offer organizations an opportunity to continuously monitor users and machines for early indicators and detection of anomalies. These sources may include email data, network activity via browser activity and related behaviors, intellectual property repository behaviors related to how content is accessed or saved, end-point data showing how files are shared or accessed, and other less conventional sources such as social media or credit reports. Connecting data from various sources and aggregating them under a comprehensive data plane can provide enhanced behavioral threat detection. Through this, robust behavioral analytics can be used to extract insights into patterns of behavior consistent with an imminent threat. At the same time, the use of behavioral analytics can also measure, accumulate, verify, and correctly identify real insider threats while preventing inaccurate classification of nonthreats. Jou concludes that the result of implementing behavioral analytics in an ethical manner can provide practical and operative intelligence while raising the question as to why implementation in this field has not occurred more quickly.

In conclusion, behavioral analytics has been previously defined as a process in which large datasets consisting of behavioral data are analyzed for the purpose of deriving insights that can serve as actionable knowledge. This definition includes three goals underlying the use of behavioral analytics, namely, to enhance organizational performance, improve decision-making, and generate insights into user behavior. Given the burgeoning presence of big data and spread of data mining techniques to analyze this data, several fields have begun to integrate behavioral analytics into their approaches for problem-solving and performance-enhancing actions. While concerns related to accuracy and ethical use of these insights remain to be addressed, behavioral analytics can present organizations and business with unprecedented opportunities to enhance business, management, and operations.

Cross-References

Further Readings

  1. Bollen, J., Mao, H., & Pepe, A. (2011). Modeling public mood and emotion: Twitter sentiment and socio-economic phenomena. Proceedings of the Fifth International Association for Advancement of Artificial Intelligence Conference on Weblogs and Social Media.Google Scholar
  2. Brown, G. M. (2007). Use of kohonen self-organizing maps and behavioral analytics to identify cross-border smuggling activity. Proceedings of the World Congress on Engineering and Computer Science.Google Scholar
  3. Carneiro, H. A., & Mylonakis, E. (2009). Google trends: A web-based tool for real-time surveillance of disease outbreaks. Clinical Infectious Diseases, 49(10).Google Scholar
  4. Davenport, T., & Harris, J. (2007). Competing on analytics: The new science of winning. Boston: Harvard Business School Press.Google Scholar
  5. Drachen, A., Sifa, R., Bauckhage, C., & Thurau, C. (2012). Guns, swords and data: Clustering of player behavior in computer games in the wild. Proceedings of the IEEE Computational Intelligence and Games.Google Scholar
  6. El-Nasr, M. S., Drachen, A., & Canossa, A. (2013). Game analytics: Maximizing the value of player data. New York: Springer Publishers.Google Scholar
  7. Fields, T. (2011). Social game design: Monetization methods and mechanics. Boca Raton: Taylor & Francis.Google Scholar
  8. Fox, P., & Hendler, J. (2011). Changing the equation on scientific data visualization. Science, 331(6018).Google Scholar
  9. Géczy, P., Izumi, N., Shotaro, A., & Hasida, K. (2008). Toward user-centric management of organizational information systems. Proceedings of the Knowledge Management International Conference, Langkawi, Malaysia (pp. 282-286).Google Scholar
  10. Kohavi, R., Rothleder, N., & Simoudis, E. (2002). Emerging trends in business analytics. Communications of the ACM, 45(8).Google Scholar
  11. Mitchell, T. M. (2009). Computer science: Mining our reality. Science, 326(5960).Google Scholar
  12. Montibeller, G., & Durbach, I. (2013). Behavioral analytics: A framework for exploring judgments and choices in large data sets. Working Paper LSE OR13.137. ISSN 2041-4668.Google Scholar
  13. Negash, S., & Gray, P. (2008). Business intelligence. Berlin/Heidelberg: Springer.Google Scholar
  14. Sifa, R., Drachen, A., Bauckhage, C., Thurau, C., & Canossa, A. (2013). Behavior evolution in tomb raider underworld. Proceedings of the IEEE Computational Intelligence and Games.Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.School of CommunicationSan Diego State UniversitySan DiegoUSA