05/2022– 07/2022 | Customer Churn Analysis

● Analyzed customer churn for an e-commerce company, performing Exploratory Data Analysis using Python and achieving a 98% model accuracy incorporating advanced machine learning techniques namely, the K-nearest neighbors (K-NN) algorithm. The goal was to understand customer behavior and provide data-driven decision targeting reduction of 15% in customer attrition and a 20% increase in customer retention rates.

04/2022– 06/2022 | Marketing and Retail Analysis

• Quantitative Analysis: Performed quantitative analysis using Python to determine strategies for maximizing profits, providing insights into demand patterns and sales performance through interactive visualizations.

• Market Basket Analysis: Identified frequently co-purchased items in the FMCG industry to improve cross-selling and product recommendations.

• Customer Segmentation: Performed RFM Analysis for customer segmentation based on orders and monetary value allowing for targeted marketing strategies and understanding payment preferences, resulting in an anticipated 20% increase in customer engagement and retention.

03/2022– 04/2022 | Sales Data Transformation and Integration

ETL operations were required to be performed on data that included sales transactions, customer information, and product details using SQL database.

• Data Extraction: Data was extracted using Microsoft SQL Server services into Python for extracting sales data.

• Data Transformation: Ensured data accuracy and consistency through processes like handling missing values, correcting data types, standardizing data formats, and updating inventory stocks and pricing using T-SQL queries in Python.

• Data Loading: Consolidated integrated data by loading transformed information into a single MySQL database, creating a simulated data warehouse.

02/2022– 03/2022 | Claim Clarity: Insights on Insurance Trends

• Data Visualization in Tableau: Created interactive Tableau dashboards to visually represent insurance claim data. Utilized dynamic visualizations, including charts, graphs, and maps, to facilitate the exploration of consumer patterns and claim trends.

• Consumer Behavior Analysis: Performed analysis to understand consumer behaviour by examining patterns within the insurance claim data, such as the frequency of claims, claim types, and demographic factors.

• Claim Trend Identification: Identified and visualized trends in insurance claims over time, enabling the identification of emerging issues or areas where the company could improve its services or policies.

• Customer Segmentation: Segmented policyholders based on their claim’s behaviour, allowing for tailored customer service and marketing strategies.

01/2022– 02/2022 | Sparkling Wine Sales Time Series Analysis

• Time Series Analysis: Performed a comprehensive time series analysis on sales data and identified

underlying patterns, trends, and seasonality, enhancing the understanding of sales dynamics.

• SARIMA Model Implementation: Utilized a Seasonal Autoregressive Integrated Moving Average (SARIMA) model to generate forecasts for future sales, providing actionable insights for business planning.

• Business Impact: Enablement of informed decision-making for marketing, inventory management, and sales strategies by leveraging quantifiable insights derived from the data analysis, leading to a 18% increase in sales forecast accuracy.