Machine Learning Based Cost prediction for Acquiring New Customers

• Published in: 2023 IEEE 13th Annual Computing and Communication Workshop and Conference (CCWC) pp. 0866 - 0872
• Main Authors: Prasad, Guduru Lakshmi Vara, Nanda, Angad Deep Singh, Darapaneni, Narayana, Bunga, Avantika, Tadepalli, Sri Keerthi, Paduri, Anwesh Reddy, Kishore, Sumit, Saini, Yogesh
• Format: Conference Proceeding
• Language: English
• Published: IEEE 08.03.2023
• Subjects: Computational modeling; Costs; Customer Acquisition Cost (CAC); Data models; Data science; Decision TreeRegressor; Exploratory Data Analysis (EDA); Grid Search CV; Measurement; Pipeline; Pipelines; Predictive models; RandomForestRegrssor; Regression models
• DOI: 10.1109/CCWC57344.2023.10099189

One of the primary goals of marketing is to acquire customers. The majority of the funds are used to acquire new customers. In evaluating a company's performance, the amount of money spent on a customer is the most important factor. This is where Customer Acquisition Cost (CAC) enter the picture. CAC is the total amount spent by an organisation to get a new customer to buy their product or service. CAC is one of the most effective performance metrics for determining the effectiveness of marketing campaigns. So, predicting the CAC is essential to the business. Data science and machine learning, on the other hand, are rapidly expanding and are now being used to solve the majority of marketing problems. Data science can aid in the analysis of marketing strategies and the discovery of hidden patterns. Machine learning can be used by marketers to forecast CAC based on given features, and data analytics will assist the company in identifying customer needs and developing various strategies. Also, machine learning helps in identifying and classifying customers as well as predicting the CAC. The purpose of this study is to find the most effective and optimal model for predicting customer acquisition costs for food mart X.