Akshay Madar's Projects
Framework for 48000+ hosts & 800,000 annual visitors in New York City to generate customized and computationally efficient - lists of Airbnbs given combinations of parameters of budget, number of days of stay, availability probability of the listing and the number of reviews.
Deep dive into Amazon's top 100 ranking methodology, studying over 700 products, coupled with wide-scope ecommerce analytics solution for enhanced customer targeting and promotional outreach
Awarded 1st position in 'Google-Krenicki Hackathon' for cloud based ML framework to predict US household income for real-estate brokerage firm; using Google Colab and AWS S3
Leveraged descriptive analytics to gain actionable business insights on user behavior and current operations of Lyft bike sharing in San Francisco bay area
A bird's eye view of all my repositories - here you will find all my data science work, which I have put in place for quick brief look. Visit individual repos for a deeper dive
A data cataloging package
Implemented decision tree algo. from scratch by calculating gini impurity and information gain for performing splits
View my industry practicum for predicting amazon profitability and trade optimization using SKU bundling strategy - for a New York based Fortune 200 CPG company's ECommerce Analytics and Insights team
Implemented gradient descent in linear regression from scratch using numpy
Implemented linear regression from scratch using normal equations, and analyzed differences when compared to gradient descent approach
Implemented gradient descent and cost function for logistic regression from scratch using numpy
Convolutional Neural Network (CNN) to identify if the given image of a cell has been parasitised or is uninfected.
Implemented MILP for profit optimization as part of prescriptive analytics solution for NY based Fortune 200 CPG industry partner, using branch-and-bound algorithm
Movie Tycoon is a platform which helps movie investors by providing insights on where and whom to invest the money on?
GCP hosted product for over 1 million movie investors on HSX.com, aiding online movie trading and box-office investments by leveraging Big Data technologies like Hive and Hadoop, and Tableau dashboards
All code files for my articles on Medium
Developed a hybrid-filtering personalized news articles recommendation system which can suggest articles from popular news service providers based on reading history of twitter users who share similar interests (Collaborative filtering) and content similarity of the article and user’s tweets (Content-based filtering)
Leveraged NLP techniques such as sentiment analysis and topic modeling to analyze different stand-up comedians using LDA, lemmatization, markov models, etc.
Implemented ordinary least squares regression from scratch in python by computing root mean square error and coefficient estimates
This repository contains Spark, MLlib, PySpark and Dataframes projects
Scraped 10-K fillings from Securities and Exchange Commission
Scraped all data from quotes.toscrape.com
Scraped data from yelp.com using beautiful soup and selenium
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent