ARCHIVES

Real life data at its core isn't always clean data. In fact, most of the time, it is not. We often get data which is noisy or incomplete or lacks some important values. However, I have observed this issue in practice, again and again, when working with practical datasets. Because of this, handling uncertainty becomes a major challenge when it comes to data analytics and wecannot ignore it if we want reliable results. Most of the traditional machine learning techniques rely on specific values of the input data and do not perform well when the data is uncertain. Soft computing techniques, particularly fuzzy logic, help cope with this issue by basing reasoning on approximate rather than strict rules. This paper proposes a hybrid soft computing approach which combines machine learning and fuzzy logic aspects in order to better deal with uncertainty in data analysis. In this technique, uncertain information is represented using simple linguistic terms by fuzzy logic and Random Forest classifier is used to obtain more accurate predictions. Experiments conducted on a student performance dataset indicate that the proposed hybrid model gives accuracy of 85.6%, which is better than the standard machine learning methods. The results show that hybrid soft computing models can perform well, accurately and easily when it comes to working with uncertain data.