E-Commerce Customer Behavior Analysis
Introduction
This project aims to help businesses better understand what their customers want and what incentivizes them to place an order. By leveraging this information, business owners can offer the products, services, and associated incentives that will not only attract customers but also convert them into loyal buyers. Furthermore, the insights gained from this analysis are based on segmentation into different categories of customers, which considers purchasing patterns, membership type, and demographic information, such as gender and location. To achieve this, I used R for data cleaning and developing the visualizations, while R Shiny was utilized to deploy the analysis in an interactive and accessible format.
App link: https://ixud1l-rukundo-oreste.shinyapps.io/R_shinny_app1/
Dataset overview
This dataset provides a comprehensive view of customer behavior within an e-commerce platform. Specifically, each entry corresponds to a unique customer and offers a detailed breakdown of their interactions and transactions. Moreover, the information is intended to facilitate a nuanced analysis of customer preferences, engagement patterns, and satisfaction levels, thereby aiding businesses in making data-driven decisions to enhance the customer experience. In terms of structure, the dataset contains eleven columns: Customer ID, Gender, Age, City, Membership type, Total spend, Items purchased, Average rating, Discount applied, Days since last purchase, and Satisfaction level. Together, these columns provide a holistic overview of customer profiles and behaviors, enabling businesses to identify trends, tailor their strategies, and ultimately improve overall customer satisfaction.
Link: https://www.kaggle.com/datasets/uom190346a/e-commerce-customer-behavior-dataset
Fig.1 below is a sample of the dataset description.
Fig.1
Segmentation by Membership
Memberships are classified by spending into Bronze, Silver, and Gold for this customer set.The higher the amount the customer spends,the higher the membership level,as identified by the difference in metal values, illustrated below in Fig. 2
Fig.2
The Impact of Discounts on Different Segments
Membership
The average amount customers spend when a discount is applied indicates that Gold and Silver membersare significantly more likely to take advantage of discounts compared to Bronze members.
Given this trend, strategies can be developed specifically to enhance retention among these membership types.For example, businesses could design targeted campaigns or exclusive discount programs to maintain their loyalty.Moreover, understanding this behavior allows companies to allocate their resources more effectively towardinitiatives that drive engagement and long-term satisfaction.
Discount and Gender Fig.3
Fig.3
Regarding target demographics, the data indicates that females are more likely to take advantage of discounts than males.Therefore, understanding this trend can help businesses plan targeted marketing efforts more effectively.On the other hand, for male customers, businesses may need to explore alternative strategies to appeal tothose who require incentives beyond discounts to motivate their purchases.For example, offering loyalty rewards,exclusive products, or personalized services could be more impactful.Ultimately, such tailored approaches can help businesses better engage both demographics and drive overall customer satisfaction.
Mapping City Differences
Fig.4
City preference and performance: Customers in Houston represent the lowest average ratings, which may partly be attributed to the economic conditions and customer sentiments. Although the cost of living in Houston is lower than in New York, some Houston customers may still rate businesses poorly if they feel that the offers and services lack personalization or if their specific concerns are not being adequately addressed. To address this challenge, companies can win greater approval and secure future business in these regions by catering to local preferences and responding to regional economic fluctuations. In doing so, they can continue to deliver good value for their customers. Businesses should actively seek feedback from Houston customers to understand what matters most to them and what they expect in terms of value, quality, and service.
By aligning their products, services, and pricing with the specific values and expectations of Houston customers, businesses can foster customer satisfaction and achieve long-term success in the region. In contrast, the highest ratings come from customers in San Francisco, with New York customers close behind. This business can aim to further win over these customers by offering products and services tailored to these geographic regions or through exceptional customer service, as evidenced by the higher ratings it enjoys. Each city has its unique cultural vibe, which often includes a celebration of emerging trends that are common to both San Francisco and New York. Consequently, it is unsurprising that customers in these cities are among the most satisfied.
Future Work
Machine learning (ML) applications for e-commerce customer behavior offer a range of powerful tools for analyzing and enhancing customer interactions.(Learn more about how machine learning enhances e-commerce customer engagement.) In particular, ML has the potential to transform e-commerce by providing deeper insights into customer behavior,
enhancing personalization, and optimizing operational efficiencies. For instance, an ML-based classification tool can help businesses understand more precisely how memberships are classified into different types (categories) based on customer behavior. Additionally, it can reveal how different genders and membership types respond to various discount levels. Moreover, ML can analyze how purchasing preferences vary by city or region,thereby enabling businesses to tailor their strategies to meet specific customer needs and preferences more effectively.
Links:
Github: https://github.com/rukundeste/R-shinny-.git
Google slides:
LinkedIn: Oreste RUKUNDO
Application:https://ixud1l-rukundo-oreste.shinyapps.io/R_shinny_app1/
Attribution: Featured image on Freepik
About the Author:
Oreste RUKUNDO developed this R Shiny App as one of his projects for the New York City Data Science Academy program. Notably, R Shiny App offers a user-friendly interface with interactive data visualization and rapid prototyping. As a result, it is very well-suited for analyzing customer behavior in an e-commerce business. Furthermore, its interactivity and flexibility allow users to explore complex datasets with ease, thereby enabling deeper insights into customer preferences and trends.
About Author
