Pranav Tumkur's repositories
Predicting-CO2-emission-using-ML-Regression-models
Experimenting with various regression models, we try to arrive at the most accurate prediction of the CO2 emission of a new car model
Similar-movies-suggestions-using-Rotten-Tomatoes-and-OMDb-API
We use 2 APIs, from OMDb (Open Movie Database) and Rotten Tomatoes, to suggest the user, similar movies according to his taste and sort them using the Rotten Tomatoes rating
Profitability-Analysis-using-Monte-Carlo-simulation
Using VBA Macros, we will determine if setting up a business would be profitable 15 years down the line, subject to 9 inputs, each associated with a certain uncertainty (pun intended!) using Monte Carlo simulation.
Analyzing-the-Hottest-Topics-in-ML-using-LDA
Using LDA, we analyze a large collection of NIPS research papers from the past 3 decades, o discover the latest trends in machine learning.
AWS-Serverless-Chatbot
An AWS Lex based serverless chatbot to assist you in Booking a Trip. We combines AWS services like Lex, Polly, Lambda, Dynamo DB and Cloudwatch Logs to give you a wholesome experience of booking a hotel and car for your trip!
Perform-AB-Testing-to-determine-the-best-version-of-an-E-Commerce-website
Using SQL we analyze the AB Test results to determine which test has the best effectiveness based on customer views and order response
Predicting-Credit-Card-Approvals-Using-ML
We try to model and train an automatic credit card approval predictor using machine learning techniques, just like the real banks do!
Analysing-the-affect-of-COVID-19-on-Stock-prices-of-6-major-banks
This is an analysis of the LIVE stock prices (as on 12/06/2020) of how COVID-19 impacted the stock prices. We try to find out the banks with the biggest losses and analyse which banks would be the riskiest to invest in
Content-Recommendation-using-Similarity-metrics
We explore 2 methodologies of designing a recommendation system- Content based and using Collaborative Filtering
How-does-Super-Bowl-outcomes-affect-TV-viewership-and-halftime-performances-
In this project, we find out how TV viewership, half-time performers/musicians interact with Super Bowl scores and outcomes and analyse the trends with time.
Lobbyists_4_Good-Tweet_and_User_Analysis
We analyze tweets of Congressmen, to analyse the interest and sentiment for the cause of Lobbyists4Good
Classifying-SMS-into-spam-and-ham-using-NLP
We do a text analysis using NLP to classify whether a text SMS is spam or ham
Comparing-4-unsupervised-classification-techniques-to-Predict-Loan-Deferral-for-a-customer
We compare prediction accuracy of loan deferral for a particular customer using 4 different unsupervised classification techniques
Predicting-Cancer-using-Support-Vector-Machines
We use SVM (Support Vector Machines) to build and train a model using human cell records, and classify cells to whether the samples are benign or malignant.
Predicting-house-prices-using-Deep-Learning
In this project, we perform EDA, for the ETL of pricing data of houses in King County, WA to train and implement Deep Learning with an Artificial Neural Network, in order to predict price of a new property on the market
Predicting-if-you-would-survive-on-the-Titanic
Ever wondered what would happen if you were onboard the Titanic? Would you survive or would you die? This project serves to answer this- We use the Kaggle Titanic dataset to build an ML model in Python. We then use a Flask API to deploy the model to Heroku app; where you can simply answer 7 questions and find out whether you survive or DIE!
Predicting-Loan-Deferral-with-ANN-Hyperparamater-Optimization-and-Oversampling
In this project, we build and train a model to predict if a customer will defer on a particular loan on an imbalanced dataset. We'll build a layered ANN for this and try to make our model better using Hyperparamater Optimization, before exploring Oversampling to make it more accurate.