The bank wanted to have a granular understanding of its customer base and predict customer’s response to the marketing campaign that was conducted for one of its products to establish a customer profile to target for future marketing campaigns. An effective solution was provided to understand the effectiveness of the campaign conducted for the product.
Collecting and understanding the raw customer data based on demographics, customer behavior, transaction history etc.
Exploring the data by developing relationship between various features required for the effectiveness modelling with dashboards.
Bringing out insights by targeting groups of customers with various characteristics to understand the relationships precisely.
Concluding the analysis with comparison of various ML techniques. These techniques gave a very clear picture of the targeted customers with diverse characteristics.
The analysis gave a clear understanding of every feature of customers affecting the marketing campaign.
They came to know the appropriate seasons and time factors which affected the campaign to target more efficiently in the future.
It prevented some customers from receiving undesirable advertisements from the campaign which raised customer satisfaction.
The bank got clarity on the accurate information by cutting down unnecessary strategies for the marketing and the subscriptions for the product raised by 10%.
The bank understood the risk profiling of the impact of marital status and occupation on the campaign and this helped them to carefully decide the likelihood of subscription.
The customer satisfaction from the campaign was measured and it raised by 5% by carefully reviewing the necessities of the campaign.
This helped the bank to focus on certain metrics which responded very well in the analysis to understand the sensitivity of the effectiveness of the campaign and helped out to overcome the bottlenecks of various other traditional ways of marketing the product.