Anirban Pal

About Me:
Data is fun. I love playing with data. I transitioned into Analytics and Data Science from a Business Intelligence background. Naturally, visual story telling and creating actionable insights from raw data were my interest. As I learned Machine Learning and advanced analytics, I felt the need for a git existence for all my side projects. This page serves the purpose.

Contact:

View My GitHub Profile

Portfolio

Bigmart Product Sales Prediction

This project relates to retail domain and basically is a machine learning model to find out factors significant for product sales.




—

Hotel Recommendation

All online travel agencies are scrambling to meet the Artificial Intelligence driven personalization standard set by Amazon and Netflix. In addition, the world of online travel has become a highly competitive space where brands try to capture our attention (and wallet) with recommending, comparing, matching, and sharing. For this assignment, we aim to create the optimal hotel recommendations for Expedia’s users that are searching for a hotel to book. For this assignment, you need to predict which “hotel cluster” the user is likely to book, given his (or her) search details.





—

Data Visualization

This project has sample of creating various charts in both R and Python. For R, the intention is to ultimately create an R package and parameterize those various chart types for ease of use.




—

LA Bike Share Model

Intent of the proect is to

  1. Create a predictive model for predicting the usage rate for a given station, on a given day and hour. This helps to figure out the number of bikes that should be in stock to handle the demand of the riders.
  2. Classifying the stations based on the number of bikes they rent – using unsupervised clustering algorithms.
  3. Predicting passholder that generates more revenue. For this predictive modelling, the cost for each pass holder type is taken from their website. This modelling is based on the assumption that bike rental costs are more or less same through out the period for which data was considered.


—

Movie Recomendation Engine

This is a recommendation engine that suggests movies to an user, based on the selections the user has done before. The project is still in progress.




—

Fifa 2019 Analysis and Modelling

The Fédération Internationale de Football Association or FIFA is a non-profit organization which describes itself as an international governing body of association football, fútsal, beach soccer, and efootball. It is the highest governing body of football. Using the player stats and data, the project intends to do exploration of facts and questions like player rating and skills, strength of a team at a particular position, player pricing, predicting the Value of a player based on his attributes, and predicting players position using the skill ratings.



—

Webscraping in Python

In this program, I am collecting wether data for my current location from weather.gov. Then I am putting it in a pandas data frame, doing basic clean up and doing some analysis on the data.



—

R Bullet Chart

A function that primarily uses ggplot package in R to produce bullet chart, which is an important graph type but natively not avialble in any of the graphing packages.

The project is being tested locally.



—

Neural Network Classifier

This project is a demonstration of Neural Network using Python.

The project is being tested locally.




—

connectR

The project is being tested locally.

Exploratory-Data-Analysis

This project is demostration of end to end exploratory data analysis. The steps comprise Data Acquisition, Data Cleansing, Data Transformation, Basic Visualization and Data Analysis.