Predicting The Outcome Of The Horse Race Using Data Mining Technique

The sole purpose of the research is to ascertain the outcome of the horse race with higher degree of accuracy using advanced data mining techniques. The difference between the existing predictive models and this model will be choosing the relevant attributes by knowing their weights and how much do they contribute in finding their label variable. Hence ensuring that the model takes into consideration only the most relevant attributes and neglects the less relevant attributes thereby reducing the noise in the system. The most efficient data mining techniques are implemented on the most relevant data for the prediction of the outcome of the horse race. Therefore, a sensible model is created, and efficiency of the system is checked by calculating its accuracy. The research is carried across two datasets, one is web scrapped from the live website and the other dataset from the data repository. The difference between their efficiency is showcased to explain the importance of choosing the attributes or features contributing to build an efficient model