Insights

Research Questions

The project discovers different analytics insights about the customer behaviour through answering the formulated Research Questions

RQ1: Are customers willing to travel long distances to purchase products?

Approach: Classifying the data based on distances and decision factors

Observation: It was found out that the majority of the customers are ready to travel long distances to purchase products and this is affected by certain factors.

Business Applications: Understand the behaviour trend of the majority of the customers related to long-distance travel to purchase products, Paves way for further understanding the reasons for such majority trends and then devise strategies in the context of the store locations coupled with enhancing the factors influencing such trends and thus generating more revenue for the business with increased customer satisfaction.

RQ2: What are the factors that contribute towards the long distance travel of the customer to purchase products?

Approach: Identifying the factors for the long-distance travel of the majority of the customers

Observation: Responsible factors for the majority of the customer trend towards long-distance travel were determined and It was observed that 'Satisfaction' is a key role factor affecting a customer's decision-making process.

Business Applications: Devise strategies to enhance the observed most important factors facilitating customer satisfaction & retention, Further paves way for a steady business growth.

RQ3: What is the maximum likelihood of a customer to select a particular shop?

Approach: Predicting the shop most likely to be selected by a new customer

Observation: It was observed that the predictive model based on Decision tree will output better results in predicting the maximum likelihood of a new customer to select a particular shop.

Business Applications: Understand which shops in the retail chain are most likely to be preferred by new customers, Facilitates towards better stock management to meet the increasing customer demands, Devise different strategies accordingly to increase profit and attract new customers in different shops.

RQ4: What are the different customer segments based on their purchase behaviour?

Approach: Clustering the data based on the shops customers shop the most

Observation: Five customer segments were detected based on the customer's purchase behaviour and further partitioning these segments revealed the specific customers belonging to the five different shops.

Business Applications: Develop a specific strategy for each cluster base, Understand the purchase behaviour of customers by keeping a track of customers over months and detecting the number of customers moving from one cluster to other which can help to better organize strategies to increase revenue at different shops, Better focus their marketing efforts on the right customers visualized through Customer Segmentation as to Discounts and offers related to a particular shop can be sent to only the customers who usually purchase at the particular shop without bothering the customers of other shops. Thus, targeting the right customers for the right deals can help to cut-down the marketing costs, generate more revenue and increase customer satisfaction.

RQ4: Which are the Top 100 customers that are most profitable in terms of revenue generation for each shop?

Approach: Ranking the Top 100 profitable customers for each shop

Observation: Top 100 customers that spend the most amount of money in each of the 5 shops based on their loyalty score were ranked and determined. Further, Top Ranked 5 customers for each shop were visualized.

Business Applications: Identify the customers who contribute majorly to the revenue of the respective shops, Further formulate reward schemes to retain the high-value customer base, Paves way to transform satisfied loyal customers as advocates for the business.