Spending Pattern Visualization Using Unsupervised Machine Learning.

As the amount of financial data generated grows yearly, there is a growing need to leverage this data to develop customized financial products to meet individual users' unique needs and preferences. This study proposes a method for identifying potential spending patterns based on categorized financial transactions. Different clustering and outlier detection algorithms are compared using various internal validation metrics and empirical analysis of cluster balancing. A visualization of the spending patterns is created from the proposed method and validated by an expert in the domain in order to extract more insights based on user behavior. The visualization was found to be helpful when analyzing for insights into spending pattern.