Projects
Machine Learning
Book Recommender System
- Formulated a model that helps users find desired number of similar books to a given book title
- Explored data and ranked books and authors based on ratings and reviews filtered by count of ratings
- Used Machine Learning (Python) to build the system
Check out the project here
Instagram Sentiment Analysis
- Analyzed the sentiment of 9000 posts on #indianeconomy on Instagram
- Used PhantomBuster to scrape live data and Textblob (Python) to obtain polarity and subjectivity of statements
Check out the project here
Predictive Purchase Project
- Understood online shopping purchasing pattern and predicted if a purchase would be made using Machine Learning (Python)
- Used user's session data having 21 attributes for more than 21000 users to build the model
Check out the project here
Economic Research
Analysis of Digital India Land Records Modernization Programme
- Obtained data for a total of 36 states and union territories in India from the website of Digital India Land Records Modernization Programme
under Department of Land Resources, Ministry of Rural Development, GoI
- Did exploratory data analysis for total number of cadastral maps, maps in good condition and number of digitized maps
- Ran linear regressions to find the relationship between several variables including number of maps, number of digitized maps,
number of maps in good condition, financial allocations by central government, overall governance , public infrastructure and
economic governance among others
- Used libraries pdftools, tidyverse, dplyr of R programming language
Check out the project here
Analysis of effect of multiple demographic factors on Life Expectancy at Birth
- Did exploratory data analysis
- Ran multiple linear regression to find the relationship between life expectancy at birth (regressand) and other demographic factors (incl. GDP, Population, Child Mortality, Literacy and Carbon Emission among others)
- Checked for assumptions of the Classical Linear Regression Model
- Used libraries haven, corrplot, car, alr4 and faraway of R programming language
Check out the project here
Analysis of Workforce Participation in Haryana and Kerala
- Analyzed data obtained from Time Use Survey of India, conducted by NSSO (GoI)
- Observed the occupational differences of people in Haryana and Kerala in terms of participation in
i. paid and unpaid activities
ii. engagement in various types of enterprises
iii. location of performance of activity
- Used MS Excel for data analysis and Tableau for data visualisation
Business Data Management
Analysis of Delivery Delays and Ranking of Personnel for CODEX Solutions Pvt Ltd
- Analyzed delivery delays with respect to SKUs and Customers for a medical equipment manufacturing company based in Pune
- Ranked the delivery personnel of the company using a specified rubric