RideMovi Data Analysis: Users Profiling

The 21st century brings an era of Big Data, where information belongs to every aspect of our lives. It presents an unprecedented opportunity for companies to leverage their data to enhance business performance. Various methods and techniques are available, tailored to a company's needs, expectations, and goals. One such innovative method is customer profiling, a robust data analysis approach that can significantly enhance the quality and quantity of services and goods offered by companies. In this Thesis, I explore the application of customer profiling using the RideMovi bike-sharing service dataset. The dataset is thoroughly analyzed and focused on segmenting users into distinct profiles. These profiles are designed based on the identification through selection of characteristic Points of Interest (PoIs). Utilizing these PoIs, I measure the distances between each point and the starting or ending locations of individual rides. Furthermore, I conduct a comparative analysis across different user profiles, examining metrics such as ride frequency, distance traveled, and duration. These metrics are evaluated on both a monthly and weekly basis. Additionally, an investigation is undertaken to uncover potential correlations between obtained results and prevailing weather conditions. Through this study, I aim to shed light on the effectiveness of customer profiling as a strategic tool for businesses, offering insights into how they can optimize their services based on user behaviors and preferences. The RideMovi dataset serves as a valuable case study, illustrating the practical applications and benefits of this approach in the context of a bike-sharing service.