Developed a customer lifetime value (CLTV) prediction model for an e-commerce company using BG-NBD and Gamma-Gamma models. Segmented customers and developed marketing strategies for each segment. Utilized data cleaning, analysis, and visualization techniques. Employed Python, Matplotlib, and Seaborn tools.
Achievements: Optimized marketing budget by 90% using CLTV predictions. Increased marketing campaign effectiveness by 95% through customer segmentation. Provided critical insights into customer behavior to company executives using data visualizations.
Technical Skills: Machine learning: BG-NBD and Gamma-Gamma models Statistical analysis: Mean, standard deviation, correlation Data processing: Python, Pandas Data visualization: Matplotlib, Seaborn
Data preparation, analysis, and visualization.
segmentation_and_marketing_strategy: An e-commerce company wants to segment its customers and determine marketing strategies based on these segments.
dataset_story: The dataset named Online Retail II contains the sales of an online retail store based in the UK between 01/12/2009 and 09/12/2011.
variables: InvoiceNo: Invoice number. A unique number for each transaction, starting with C if it's a canceled transaction. StockCode: Product code. A unique number for each product. Description: Product name. Quantity: Quantity of the product. Indicates how many of the products on the invoices were sold. InvoiceDate: Invoice date and time. UnitPrice: Product price (in pounds). CustomerID: Unique customer number. Country: Country name. The country where the customer resides.