SVM-based association rules for knowledge discovery and classification

Improving analysis of market basket data requires the development of approaches that lead to recommendation systems that are tailored to specifically benefit grocery chain. The main purpose of that is to find relationships existing among the sales of the products that can help retailer identify new opportunities for cross-selling their products to customers. This paper aims to discover knowledge patterns hidden in large data set that can yield more understanding to the data holders and identify new opportunities for imperative tasks including strategic planning and decision making. This paper delivers a strategy for the implementation of a systematic analysis framework built on the established principles used in data mining and machine learning. The primary goal of that is to form the foundation of what we envisage will be a new recommendation system in the market. Uniquely, our strategy seeks to implement data mining tools that will allow the analyst to interact with the data and address business questions such as promotions advertisement. We employ Apriori algorithm and support vector machine to implement our recommendation systems. Experiments are done using a real market dataset and the 0.632+ bootstrap method is used here in order to evaluate our framework. The obtained results suggest that the proposed framework will be able to generate benefits for grocery chain using a real-world grocery store data.