|dc.description.abstract||Estimation and prediction of students enrolment in a college provides, besides straightforward profit opportunities, indications to various important data and information for example information on customer fluctuation over period, thus helping in decision making especially in resource allocation. Forecasting the number of students expected to enroll in a college is therefore of prime importance to the management for both tactical and strategic management. This can be based on the available historical data and use of time series prediction.
Students' enrolment time series can be predicted with a certain degree of confidence. This is from analyzed data. Future activities can be determined from the past performances. In this project, a short forecast will be used. This is because a shorter forecast gives a more accurate result with a higher degree of confidence.
So far, the primary means of detecting trends and patterns has involved statistical methods such as statistical clustering and regression analysis. The mathematical models associated with these methods for economical forecasting, however, are linear and may fail to forecast the turning points in economic cycles because in many cases the data they model maybe highly nonlinear.
In the contemporary generation in computing, new methodologies, including neural networks, knowledge-based systems and genetic algorithms, has attracted attention for analysis of trends and patterns. In particular, neural networks are being used extensively for financial forecasting with stockmarkets, foreign exchange trading, and commodity future trading and bond yields.
Stockmarket prediction is an area of financial forecasting which attracts a great deal of attention
This research paper therefore presents a scheme for time series forecasting with a neural network.
To help evaluate the performance of the Neural Net, a benchmark Autoregression model will be developed using regression analysis. A statistical package SPSS will be used to come up with the model. A theoretical comparison of the methods (ANN and autoRegression) is provided in the conclusion.||en_US