This repo contains code and resources for random analysis projects done in R, using multiple packages such as tidyverse, tidymodels and more. Note that project files are added on an ongoing basis. Additionally, data folders and artifacts (like model objects) are not committed to this repo to avoid push conflicts due to large files.
This project focuses on analyzing Starbucks ingredients and utilizing machine learning techniques to predict the calorie content of a drink based on its ingredients.
The project explores customer segmentation in the banking industry using the k-means algorithm. It aims to identify distinct customer segments based on shared characteristics and provides insights into effective customer targeting in the banking sector. See detailed analysis write up on Medium.
A detailed analysis of CRM data from a company selling computer hardware. The primary focus was on establishing performance benchmarks, understanding sales trends, and segmenting customers to enhance sales and marketing strategies. Read the analysis write up on Medium.
A deep dive sales analysis of a global electronics retailer. The main goal is to address concerns from senior management about recent sales trends. Despite experiencing significant growth between June 2018 and Feb 2020, sales have started to return to earlier levels. There is a concern that sales could fall below the levels seen before June 2018. Through detailed data analysis, we aim to identify if there are factors contributing to the recent sales decline (post Feb 2020) and develop strategies to maintain and improve sales performance. Read the analysis write up on Medium.