Visual performance improvement analytics of predictive model for unbalanced panel data

Abstract

An unbalanced panel is a dataset in which at least one subject is not observed some times. Moreover, each subject is recorded with irregular periods and intervals. Therefore, only short trend pattern pieces exist in the data. When applying existing prediction techniques, it is challenging to create a prediction model that reflects individual subject patterns. Also, uncertainties in the predicted results emerge since the overall trend of the data is unknown. In this paper, we present a Bayesian network to predict the future trends of subjects from the unbalanced panel data. We also present a new approach to estimate the predicted intervals of the predicted results. Moreover, we propose a visual analytics system that enables us to build a prediction model from unbalanced panel data. The visual analytics system also supports performance improvement in the already designed prediction model. We evaluate the effectiveness of our system while building a predictive model according to various data patterns.

Graphic abstract

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

References

  1. Aigner W, Miksch S, Schumann H, Tominski C (2011) Visualization of time-oriented data. Springer, Berlin

    Google Scholar 

  2. Andrienko N, Andrienko G, Rinzivillo S (2014) Experiences from supporting predictive analytics of vehicle traffic. In: Proceedings of IEEE VIS Workshop VIS. IEEE, Paris, France, pp 1–4

  3. Bögl M, Aigner PF, Lammarsch T, Miksch S, Rind A (2013) Visual analytics for model selection in time series analysis. IEEE Trans Vis Comput Gr 19(12):2237–2246

    Article  Google Scholar 

  4. Bostock M, Ogievetsky V, Heer J (2011) D\(^3\) data-driven documents. IEEE Trans Vis Comput Gr 17(12):2301–2309

    Article  Google Scholar 

  5. El-Assady, Jentner M, Stein W, Fischer M, Schreck F, Keim D (2014) Predictive visual analytics: approaches for movie ratings and discussion of open research challenges. In: Proceedings IEEE VIS Workshop. IEEE, France

  6. Yeon H, Kim S, Jang Y (2017) Predictive visual analytics of event evolution for user-created context. J Vis 20(3):471–486

    Article  Google Scholar 

  7. Han D, Pan J, Guo F, Luo X, Wu Y, Zheng W, Chen W (2019) Rankbrushers: interactive analysis of temporal ranking ensembles. J Vis 22(6):1241–1255

    Article  Google Scholar 

  8. Krause J, Perer A, Ng K (2016) Interacting with predictions: visual inspection of black-box machine learning models. In: Proceedings of the 2016 CHI conference on human factors in computing systems, pp 5686–5697

  9. Krause J, Perer A, Bertini E (2014) Infuse: interactive feature selection for predictive modeling of high dimensional data. IEEE Trans Vis Comput Gr 20(12):1614–1623

    Article  Google Scholar 

  10. Liu Y, Guo Z, Zhang X, Zhang R, Zhou Z (2019) (chinavis 2019) uncertainty visualization in stratigraphic correlation based on multi-source data fusion. J Vis 22(5):1021–1038

    Article  Google Scholar 

  11. Gauld LM, Kappers J, Carlin JB, Robertson CF (2004) Height prediction from ulna length. Deve Med Child Neurol 46(7):475–480

    Article  Google Scholar 

  12. Lu Y, R Krüger DT, Wang F (2014)Integrating predictive analytics and social media. In: Proceedings of IEEE conference on visual analytics science and technology. IEEE, France, pp 193–202

  13. Malik A, Maciejewski R, Towers S, McCullough S, Ebert DS (2014) Proactive spatiotemporal resource allocation and predictive visual analytics for community policing and law enforcement. IEEE Trans Vis Comput Gr 20(12):1863–1872

    Article  Google Scholar 

  14. Hao MC, Janetzko H, Mittelstädt S, Hill W, Dayal U, Keim DA, Marwah M, Sharma RK (2011) A visual analytics approach for peak-preserving prediction of large seasonal time series. In: Computer Graphics Forum. Eurographics, UK, pp 691–700

  15. Mühlbacher T, Piringer H (2013) A partition-based framework for building and validating regression models. IEEE Trans Vis Comput Gr 19(12):1962–1971

    Article  Google Scholar 

  16. Ng K, Ghoting A, Steinhubl SR, Stewart WF, Malin B, Sun J (2014) Paramo: a parallel predictive modeling platform for healthcare analytic research using electronic health records. J Biomed Inf 48:160–170

    Article  Google Scholar 

  17. Onis M (2006) Relationship between physical growth and motor development in the who child growth standards. Acta Paediatrica 95:96–101

    Google Scholar 

  18. Rogol AD, Clark PA, Roemmich JN (2000) Growth and pubertal development in children and adolescents: effects of diet and physical activity. Am J Clin Nutr 72(2):521–528

    Article  Google Scholar 

  19. Sherar LB, Mirwald RL, Baxter-Jones AD, Thomis M (2005) Prediction of adult height using maturity-based cumulative height velocity curves. J Pediat 147(4):508–514

    Article  Google Scholar 

  20. Silventoinen K, Kaprio J, Lahelma E, Koskenvuo M (2000) Relative effect of genetic and environmental factors on body height: differences across birth cohorts among Finnish men and women. Am J Public Health 90(4):627

    Article  Google Scholar 

  21. Sun G, Zhou Z, Chang B, Tang J, Liang R (2019) Permvizor: visual analysis of multivariate permutations. J Vis 22(6):1225–1240

    Article  Google Scholar 

  22. Höllt T, Magdy A, Zhan P, Chen G, Gopalakrishnan G, Hoteit I, Hansen CD, Hadwiger M (2014) Ovis: a framework for visual analysis of ocean forecast ensembles. IEEE Trans Vis Comput Gr 20(8):1114–1126

    Article  Google Scholar 

  23. Tang H, Wei S, Zhou Z, Qian ZC, Chen YV (2019) Treeroses: outlier-centric monitoring and analysis of periodic time series data. J Vis 22(5):1005–1019

    Article  Google Scholar 

  24. Tang T, Yuan K, Tang J, Wu Y (2019) Toward the better modeling and visualization of uncertainty for streaming data. J Vis 22(1):79–93

    Article  Google Scholar 

  25. Yang B, Cao W, Tian C (2019) Visual analysis of impact factors of forest pests and diseases. J Vis 22(6):1257–1280

    Article  Google Scholar 

  26. Zhang T, Thomas K, Weiller K (2015) Predicting physical activity in 10–12 year old children: a social ecological approach. J Teach Phys Edu 34(3):517–536

    Article  Google Scholar 

Download references

Acknowledgements

This work was partly supported by Institute for Information & communication Technology Planning & Evaluation(IITP, Korea) funded by the Korea government(MSIT) (No. 2019-0-00795, Development of integrated cross-model data processing platform supporting a unified analysis of various big data models), (No. 2019-0-00136, Development of AI-Convergence Technologies for Smart City Industry Productivity Innovation). Yun Jang is the corresponding author.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Yun Jang.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Yeon, H., Son, H. & Jang, Y. Visual performance improvement analytics of predictive model for unbalanced panel data. J Vis (2021). https://doi.org/10.1007/s12650-020-00716-0

Download citation

Keywords

  • Visual analytics
  • Model optimization
  • Incomplete data