Analysis of Probabilistic Models in Artificial Intelligence Using Mathematical Statistical Methods

Zainab A.  Khudhair

Authors

Zainab A. Khudhair Branch of Mathematics and Computer Applications, Department of Applied Sciences, University of Technology, Baghdad, Iraq

Keywords:

Probabilistic Models, Mathematical Statistics, Bayesian Inference, Machine Learning, Likelihood Estimation

Abstract

Today’s AI Must Use Probabilistic Models. AI is applying probabilistic models more often so it can work in the real world. The artificial intelligence application of probability models helps mathematical statisticians to formulate, estimate and evaluate bases. We will use essential ideas from Mathematical Statistics and Probability Theory to analyze models such as Bayes’ networks, Hidden Markov Models, Gaussian Mixture Model and more.

The study employs a systematic computation method. This study analyses a range of mathematical formulations of selective probability models in conjunction with a critique of brute force statistical estimation conclusions. It uses maximum likelihood and Bayesian methods. A synthetic dataset can facilitate easy control of experiments. Models that use probabilities yield successful predictions by taking into account their uncertainty. Still, estimating parameters and assuming distributions is the basis for the model functionality.

According to the text, three tables as well as three figures offer comparisons among the models on accuracy, convergence behaviour and likelihood estimation. Bayesian-based model outperform classical ones when data is lacking, and likelihood-based models do when data is plentiful. This researcher seeks to reduce the gap between theory and application in statistics.

This article will set up the statistical framework in which probablisitic models operate. Considering data and computational restrictions, we advise on a probabilistic model.

References

S. S. Suyunboevich and D. O. Djuraevich, “The application of mathematics in solving physical problems,” Shokh Articles Library, vol. 1, no. 1, 2026.

J. Min, X. Song, S. Zheng, C. B. King, X. Deng, and Y. Hong, “Applied statistics in the era of artificial intelligence: A review and vision,” Applied Stochastic Models in Business and Industry, vol. 42, no. 2, Art. no. e70075, 2026.

A. K. Shukla and M. K. Awasthi, “Mathematical foundations for modeling complex systems,” in Complex Engineering Systems–Modeling and Optimization: Multi-Objective Analysis and Smart Manufacturing Applications, p. 17, 2026.

N. Nisha and M. Abouagwa, “Mathematics: The backbone of smart business decisions,” in Marketing Strategies for Total Quality Management in Hospitality Excellence, pp. 187–210, 2026.

X. Qian, “The logical positioning and value of probability theory in the mathematical world from the perspective of an introduction,” American Journal of Big Data, vol. 7, no. 1, pp. 35–43, 2026.

B. J. Reich and S. K. Ghosh, Bayesian Statistical Methods: With Applications to Machine Learning. Boca Raton, FL, USA: Chapman and Hall/CRC, 2026.

S. J. Dhanavade, “From symbolic AI to foundation models: A comprehensive review of the evolution of artificial intelligence up to December 2025,” 2026.

A. Krause and J. Hübotter, “Probabilistic artificial intelligence,” arXiv preprint arXiv:2502.05244, 2025.

S. Ghani and S. Kumari, “A novel tool for probabilistic modeling of liquefaction behavior in alluvial soil,” Georisk: Assessment and Management of Risk for Engineered Systems and Geohazards, vol. 19, no. 1, pp. 134–157, 2025.

A. Hussain, K. Mahmood, I. Ibrahim, A. Jameel, S. Nawaz, and M. Tashtoush, “Parameters estimation of the Gompertz-Makeham process in non-homogeneous Poisson processes: Using modified maximum likelihood estimation and artificial intelligence methods,” Mathematics and Statistics, vol. 13, no. 1, pp. 1–11, 2025.

A. Vashistha, T. A. Alghamdi, S. A. Almalki, W. M. Ead, and G. Kaur, “AI-driven intrusion prevention system: Leveraging mathematical foundations for advanced threats detection,” International Journal of Information Technology, vol. 17, no. 7, pp. 4365–4370, 2025.

M. U. Kraemer et al., “Artificial intelligence for modelling infectious disease epidemics,” Nature, vol. 638, no. 8051, pp. 623–635, 2025.

Y. Guo, B. Yang, S. Alqawzai, K. Chen, and D. Kong, “Machine learning-based and interpretable models for predicting the resistance and probability of progressive collapse of steel frame-composite floor structures,” Engineering Structures, vol. 332, Art. no. 120089, 2025.

Z. Huang, Y. Wei, and Y. Chen, “Denoising diffusion probabilistic models are optimally adaptive to unknown low dimensionality,” Mathematics of Operations Research, 2026.

I. Kozlova and M. Saidakhmedova, “A probabilistic-statistical approach,” in Artificial Intelligence in Models, Methods and Applications, p. 185, 2023.

Y. A. Abolade, “Bridging mathematical foundations and intelligent systems: A statistical and machine learning approach,” Communication in Physical Sciences, vol. 9, no. 4, pp. 774–784, 2023.