Embedded Files
I participated in the AI and Data Science Program offered by the MIT Institute for Data, Systems, and Society from April to August 2026. The program focused on using responsible AI, data, and statistical methods to address practical business challenges.
Throughout the program, I worked on projects that involved solving real-world business problems using AI and machine learning techniques. These projects strengthened my ability to use data-driven approaches for business decision-making, develop practical recommendations, and translate analytical findings into actionable business solutions.
Link to certficate: https://www.mygreatlearning.com/certificate/LLYZJNHN
Project 1: Amazon Product Recommendation System
The rapid growth of e-commerce has created an overwhelming number of product choices for consumers. Recommender systems help businesses address this challenge by providing personalized product suggestions based on customer preferences and behavior, improving customer engagement and supporting sales.
Objectives: To build a recommendation system to recommend products to customers based on their previous ratings for other products. You have a collection of labeled data of Amazon reviews of products. The goal is to extract meaningful insights from the data and build a recommendation system that helps in recommending products to online consumers.
Data: The Amazon dataset contains information on userid, productid, rating
Software and Analytical Tools: Pandas, NumPy, Matplotlib, Seaborn, Scikit-learn, Surprise); Rank-based Recommendation System, Collaborative Filtering Recommendation Systems, and Model-Based Collaborative Filtering-Matrix Factorization.
Business Impact: The Singular Value Decomposition (SVD) model, particularly its optimized version, provided personalized predictions for user-item pairs. Although its RMSE (was slightly higher than the best item-item KNN, its ability to generate predictions for novel interactions makes it more suitable for a practical recommendation system. Recommended exploring hybrid recommendation models, incorporating content-based features, or experimenting with more advanced techniques like deep learning-based recommenders to further enhance personalization and predictive accuracy.
Project 2: Customer Personality Segmentation
Aim: To develop personalised mareketing campaigns to increase conversion rate and create effective retention strategies for high-value customers while optimising resource allocation such as inventory managment, pricing strategies and store layouts.
Objectives: To identify distinct customers segement to enhance marekting efficiency and enhance customer experience.
Data: Historical Unstructured data from 1893 to 1996 for the retail X on customer demographics, Spending information, Purchase and Campaign interaction, Shopping behavior
Software and Analytical Tools: Python (Pandas, NumPy, Matplotlib, Scikit-learn, SciPy, Yellowbrick); Kmeans Clustering, Exploratory Data Analysis
Business Impact: Developed targeted marketing strategies for different customer segments, including online promotions for price-sensitive, lower-income customers with frequent website visits and relationship-focused campaigns emphasizing convenience, trust, and exclusivity for high-value customers.
Project 3: Lead Conversion Prediction and Customer Profiling for the EdTech company ExtraaLearn
ExtraaLearn is an EdTech company offering programs in emerging technologies to help students and professionals upskill and reskill. The company generates leads through digital channels such as social media, website interactions, brochure downloads, and email inquiries. These leads are then nurtured through sales calls and emails with the goal of converting them into paying customers. The key business challenge is identifying leads with the highest likelihood of conversion to improve sales targeting and resource allocation.
Objectives: To develop an ML model to predict lead conversion and identify key factors driving customer conversion.
Data: Lead-level data capturing demographic characteristics, digital engagement, marketing exposure, and conversion outcomes. Variables include age, occupation, first interaction channel, profile completion, website visits, time spent on the website, page views per visit, last activity, advertising exposure across print and digital media, educational channels, referrals, and lead conversion status.
Software and Analytical Tools: Python (Pandas, NumPy, Matplotlib, Seaborn, Statsmodels, Scikit-learn); Decision Trees, Random Forest
Business Impact: Recommended prioritizing website engagement, encouraging profile completion through targeted incentives, and personalizing marketing campaigns by age group. Suggested using the Random Forest model to identify high-potential leads and prioritize sales follow-up, improving resource allocation and conversion targeting.
Page updated
Google Sites
Report abuse