Qualification: 
Ph.D, MPhil
cs_rajitha@cb.amrita.edu

Dr. Rajitha C. S. currently serves as Assistant Professor at the Department of Mathematics, School of Engineering, Coimbatore.

Education

  • 2019: Ph. D. 
    Bhararthiar University
  • 2014: M. Phil. 
  • Bhararthiar University

Publications

Publication Type: Journal Article

Year of Publication Title

2019

Rajitha C. S. and Sakthivel, K. M., “Zero-Inflated Negative Binomial-Lindley Distribution and its Application”, Far East Journal of Theoretical Statistics, vol. 55, no. 2, pp. 101-112, 2019.

2019

Rajitha C. S. and Sakthivel, K. M., “Model Selection for Count Data with Excess Number of Zero Counts”, American Journal of Applied Mathematics and Statistics, vol. 7, no. 1, pp. 43-51, 2019.[Abstract]


Zero inflated models have been widely studied in statistical literature. Zero inflated Poisson model and hurdle model are the most commonly used models for modeling the overdispersed count data. In adddition to this, recent studies shows that a nonparametric and data dependent technique known as artificial neural networks (ANN) produce better performance for modeling the over dispersed and zero inflated count data. In this paper, we compared the performance of different models such as zero inflated Poisson model, hurdle model and ANN for modelling the zero inflated count data in terms of standardized MSE, SE, bias and relative efficiency. An application study is carried out for both the simulated data set and real data set. Also for checking the suitability of these three models, we verified the group membership of the models, by adopting three classification techniques known as discriminant analysis, CART and random forest. We proposed an algorithm for selecting the better model among a set of models and computed the misclassification rates for a zero inflated count data set using different classifiers.

More »»

2018

Rajitha C. S. and Sakthivel, K. M., “Estimation of Zero-Inflation Parameter in Zero-Inflated Poisson Model”, International Journal of Mathematics Trends and Technology (IJMTT), vol. 56, no. 2, 2018.[Abstract]


The modelling of count data is extensively used in many fields of research. There is handful of zero-inflated probability models available in literature. Among these models, zero inflated Poisson distribution is one of the widely used models for modelling data with excess number of zeros. In all the zero-inflated models, one can have parameter called zero-inflation parameter which is in addition to the number of parameters in underlying distribution. The estimation of the zero-inflation parameter of the zeroinflated Poisson (ZIP) models by MLE do not have an explicit expression and solved iteratively by using modern computing techniques. In this paper, we proposed a probability based inflation estimator (PBIE) for making inferences about the inflation parameter of the ZIP model and also studied the performance of the proposed estimator for simulated data.

More »»

2018

Rajitha C. S. and Sakthivel, K. M., “Application of Kernel Density Estimation in Chain Ladder Method for Claim Reserving”, International Journal of Scientific Research in Mathematical and Statistical Sciences, vol. 5, no. 6, 2018.

2017

K. M. Sakthivel, Rajitha C. S., and Alshad, K. B., “Zero-Inflated Negative Binomial-Sushila Distribution and Its Application”, International Journal of Pure and Applied Mathematics, vol. 117, no. 13, pp. 117-126, 2017.[Abstract]


In statistics literature, there is significant study of mixtures and compound probability distributions used for count model especially for the data contains excess zeros. In this paper, we introduce a new probability distribution which is obtained as a compound of zero-inflated negative binomial (ZINB) distribution and Sushila distribution and it is named as zero-inflated negative binomial-Sushila (ZINB-S) distribution. It can be used as an alternative and effective way of modeling over dispersed count data. The probability mass function (PMF) and some vital characteristics of ZINB-S distribution are derived. MLE method is employed for estimating the model parameters. Further the example is given to show that ZINB-S provides better fit compare to traditional models for over dispersed count data. AMS Subject Classification: 2010: 62F10; 62P05

More »»

2017

Rajitha C. S. and Sakthivel, K. M., “Artificial Intelligence for Estimation of Future Claim Frequency in Non-Life Insurance”, Global Journal of Pure and Applied Mathematics, vol. 13, no. 6, pp. 1701-1710, 2017.[Abstract]


The essential feature of an insurance practice is to set the premium at the beginning of the insurance contract. To determine the correct premium for next year in an insurance company, precise and reliable estimate of the number of occurrence of claims and the total claim amounts is extremely important. Different methods are available in the literature for predicting the claim frequency of a policy for forthcoming years such as Generalized linear models (GLMs), Poisson regression models, Credibility models, Bayesian Models etc. But due to the heterogeneous nature of policies these methods does not produce exact and reliable prediction of future claim frequencies. Besides these conventional statistical methods depends largely on some limiting assumptions such as linearity, normality, independence among predictor variables and a pre-existing functional form relating the criterion variable and predictive variables etc. Recent studies in Artificial Intelligence show that Artificial Neural Networks (ANN) is powerful tools for prediction tasks due to their nonlinear nonparametric adaptive learning properties. In this paper, we developed the procedure for predicting the future claim frequency of insurance portfolio in general insurance using ANN with use of Bayesian credibility inputs with suitable illustration.

More »»

2017

Rajitha C. S. and Sakthivel, K. M., “A Comparative Study of Zero-Inflated, Hurdle Models with Artificial Neural Network in Claim Count Modeling”, International Journal of Statistics and Systems, vol. 12, no. 2, pp. 265-276, 2017.[Abstract]


Modeling of claim frequency is a vital factor in the non-life insurance industry. The claim count data in non-life insurance may not follow the traditional regression count data models with the use of Poisson or negative binomial distribution in numerous circumstances due to excessive number of zeros in the real data set. If the excessive number of zeros is not considered with sufficient weight, it will lead to information shortage to get a accurate rate making for the non-life insurance portfolio. In this paper we compared different claim count models such as zero-inflated Poisson (ZIP) regression model, hurdle model with back propagation neural network (BPNN) for modeling the count data which has excessive number of zeros. We shown from our empirical study that BPNN outperforms the conventionally used models and provided better fit to claim count data in terms of mean squared error (MSE).

More »»

2017

Rajitha C. S. and Sakthivel, K. M., “Comparative Study of Modeling on Claim Frequency in Non-life Insurance”, International Journal of Statistika and Mathematika, vol. 24, no. 1, pp. 01-06, 2017.

2017

K. M. Sakthivel and Rajitha C. S., “A Study of Claim Size Estimation Using General Linear Model and Artificial Neural Network”, Global Journal of Pure and Applied Mathematics, vol. 13, no. Special Issue 2, pp. 505-514, 2017.

2016

Rajitha C. S. and Sakthivel, K. M., “Kernel Density Estimation for Claim Size Distributions Using Shifted Power Transformation”, 2016.[Abstract]


This paper presents density estimation of univariate claim severity distributions using kernel density estimation. We applied transformations to data prior to implement kernel density estimation so as to ensure the data is symmetry for the purpose of applying Gaussian methods. The paper presents non-parametric method of obtaining density for univariate claim severity distributions with goodness fits analysis for Danish insurance data on fire loss claims.

More »»

Publication Type: Conference Proceedings

Year of Publication Title

2018

K. M. Sakthivel, Rajitha C. S., and Alshad, K. B., “Statistical Modeling of Count Data using Negative Binomial - Generalized Lindley Distribution”, INTERNATIONAL CONFERENCE ON COMPUTING INTELLIGENCE AND DATA SCIENCE (ICCIDS 2018), vol. 6. pp. 01-06, 2018.

2018

K. M. Sakthivel, Rajitha C. S., and Rajkumar, J., “Negative Binomial Sujatha Distribution and its Applications in Analysis of Overdispersed Count Data”, International Conference on Advances in Pure and Applied Mathematics, ICPAM 2018, vol. 7. 2018.

2017

K. M. Sakthivel and Rajitha C. S., “Estimation of Claim Severity in Non-Life Insurance: A Non-Parametric Approach”, ICITCSA 2017 Pioneer College of Arts and Science, Coimbatore, vol. 6. 2017.