Count Predictive Model with Mixed Categorical and Count Explanatory Variables

0575361 - ÚTIA 2024 RIV US eng C - Conference Paper (international conference)
Uglickich, Evženie - Nagy, Ivan - Reznychenko, T.
Count Predictive Model with Mixed Categorical and Count Explanatory Variables.
Proceedings of the The 12th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS) IDAACS'2023. Piscataway: IEEE, 2023, s. 51-56. ISBN 979-8-3503-5804-9. E-ISSN 2770-4254.
[The 12th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS) IDAACS'2023. Dortmund (DE), 07.09.2023-09.09.2023]
R&D Projects: GA MŠMT 8A21009
Institutional support: RVO:67985556
Keywords : count data * Poisson mixtures * Poisson regression * recursive Bayesian mixture estimation
OECD category: Statistics and probability
http://library.utia.cas.cz/separaty/2023/ZS/uglickich-0575361.pdf

The paper considers the problem of online prediction of a count variable based on real-time explanatory data of mixed count and categorical nature. The presented solution is based on (i) recursive Bayesian estimation of a mixture model of Poisson-distributed explanatory counts, using the categorical explanatory variable as a measurable pointer of the mixture, (ii) construction of a mixture of local Poisson regressions on the clustered data, and (iii) use of the pre-estimated mixtures for online prediction of the target count using actual measured explanatory data. The latter is one of the main contributions of the proposed approach. In addition, the dynamic model of the categorical explanatory variable preserves the functionality of the algorithm in case of its measurement failure. The experiments with simulations and real data report lower prediction errors compared to theoretical counterparts.
Permanent Link: https://hdl.handle.net/11104/0345384