apurvashekhar,Apurva Shekhar,github

I am a recent graduate of Masters in Business Analytics at Santa Clara University, 2020. Along with my coursework, I worked as a part-time business analyst at an IoT startup, Atollogy Inc for 7 months. I gained practical knowledge of working with large, messy datasets, and wrote complex SQL queries to generate actionable business insights. I got the opportunity to collaborate with the data engineer and customer success teams to understand the business need of the client. This experience helped me to become fluent in curate Tableau dashboards to highlight key metrics to support the client's operational workflow.

Currently, I am working on honing my skills to write efficient code to handle large datasets and reduce runtime. During my free time, I love to travel, bake and workout!

Langauges and Tools:

Reach out to me:

Data Analyst
Business Analyst

Stats:

Top Languages:

Apurva Shekhar's Projects

airbnbanalysis

Data Analysis on Airbnb for 6 cities- NY, Washington DC, Chicago, San Francisco, Boston, and Los Angeles.

algorithms

This repositories will contain algorithms programmes.

coursera-python

Completed the 5- course Python specialisation course by University of Michigan (via Coursera).

leetcode

Solution of SQL questions in Leetcode

master_sql_for_data_science_udemy

Wrote complex sql queries using subqueries, correlated subqueries, window functions. This repository contains assignments as well as mini assignments given during the lectures.

neural_machine_translator

Transformer NN architecture was introduced by Google in 2017 in their paper ‘Attention is all you need’. Transformers try to solve the problem of parallelization by using a concept called ‘Attention’. In this repo you'll find transformers being used to speed up sequence to sequence models to translate English to French and Spanish.

spoon-knife

This repo is for demonstration purposes only.

us_accident_analysis

This is a countrywide car accident dataset, which covers 49 states of the USA. The accident data are collected from February 2016 to June 2020. An interesting analysis on the trends of these accidents.

us_unemployment_time_series

The purpose of this report is to identify the most appropriate model to forecast future unemployment rate in the US using the historical data. We present an in-depth study of the forecasts for the monthly U.S. unemployment rate using various time series models and comparing them to further our understanding of the strengths and deficiencies of these methods.