• Ramsai Jagadish Yenugadhati
• Bala Nagendra Babu
• Pallav Kumar Baruah
• Satya Sai Baba Mudigonda
• Rohan Yashraj Gupta, Phani Krishna Kandala

The profitability and competitiveness of the motor insurance business are directly dependent on accurately estimating the claim count. Statistically, it can be seen as a Regression problem. Claim count is a discrete random variable that allows only discrete positive values which is count data. Negative Binomial (NB2), Poisson, Quasi-Poisson, and Artificial Neural Network Models are used for Regression analysis on discrete data. For this work crash analysis system (CAS) dataset is used. The performance of the models is measured using various Error metrics. It is found that the Negative Binomial regression model performs better than the other models with a mean square error of 0.09 and a root mean square error of 0.30.

Generalized Linear models, claim counts, Neural Networks, Crash Analysis System,

"ESTIMATION OF NUMBER OF CLAIMS IN MOTOR INSURANCE USING GENERALISED LINEAR MODELS and ARTIFICIAL NEURAL NETWORKS.", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 6, page no.k1-k13, June-2022, Available :http://www.jetir.org/papers/JETIR2206A01.pdf

"ESTIMATION OF NUMBER OF CLAIMS IN MOTOR INSURANCE USING GENERALISED LINEAR MODELS and ARTIFICIAL NEURAL NETWORKS.", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 6, page no. ppk1-k13, June-2022, Available at : http://www.jetir.org/papers/JETIR2206A01.pdf