Tag Archives: Mean Square Error

An Improved Model for Financial Institutions Loan Management System: A Machine Learning Approach (Published)

The inability of financial instructions, especially the Microfinance Banks, to forecast for the need of borrowers in order to make provision for them has been a cause for concern. Applications are made and most times the reply is that funds are not available. This paper demonstrated the design and implementation of neural network model for development of an improved loan-based application management system. The back propagation algorithm was used to train the neural network model to ascertain corrections between the data and to obtain the threshold value. The data was collected over a period of three years from UCL machine learning repository.  The system was designed using object oriented methodology and implemented with Java programming language and MATLAB. The results obtained showed the mean squared error values 1.09104e-12, 5.56228e-9 and 5.564314e-4 for the training, testing and validation respectively. It was seen from the result that neural network can forecast the financial market with minimum error.

Keywords: Mean Square Error, Neural network, Regression, Validation, and Forecasting.

An Empirical Study on Modified Maximum Likelihood Estimator and Maximum Likelihood Estimator for Inverse Weibull Distribution by Using Type Ii Censored Sample (Review Completed - Accepted)

Parameter estimation become complicated when censoring is present in the sample Some time it is not possible to give a mathematical expression of estimated values of parameters in Maximum Likelihood (ML) method. .Dayyeh and Sawi (1996) used the Mehrotra and Nanda (1974) MML technique. They replaced the intractable term of likelihood equations with its expectation, to get the estimators of location parameter by considering the scale parameter equal to 1 of logistic distribution in right Type ll censored sample. Kambo (1978) derived the explicit solution for ML estimator of two parameter exponential distribution in the case of doubly type ll censored sample. In this paper MML estimator and ML estimator of inverse weibull distribution by using type II censored sample have been derived and compared in term of asymptotic variances and mean square error. The purpose of conducting the empirical study is to study the closeness of MML estimators to ML estimator, and relative efficiency of censored sample to complete sample.

Keywords: Asymptotic Variances, Bias, Inverse weibull distribution Order Statistics, Maximum Likelihood Estimator, Mean Square Error, Modified Maximum Likelihood Estimator, Type II censored sample