Saurabh

Work History Data Engineer: Cians Analytics Private Limited – Gurugram, Haryana 09/2021 to present

 Create and maintain ETL Processes on Databricks (using AWS - S3, PySpark)

 Import new data sets directly from the vendor

 Maintain the process to convert raw data into meaningful output for US based Data Science client

 Create Quality Checks for the data thus produced by the process to identify bad data

 Client interaction daily for requirement gathering Senior Analyst: Cians Analytics Private Limited – Gurugram, Haryana 09/2021 to present

 Conducted economic analysis and estimation on different econometrics macros

 Collected data of econometrics macros variable from different sources

 Find out the best macros variable to estimate PPP (Purchasing Power Parity) of each country

 Applied different transformation method to remove trained and seasonal effect of time series data

 Used ARIMA model to predict the econometrics variable.

 Generated plots of macros country-wise using Plotly and saved the results in pdf Analyst: Tata Consultancy Services– Bangalore, Karnataka 10/2019 to 08/2021

 Collaborated closely with product management to define and prioritize the technical vision of product

 Downloaded PDF from different website using web scraping

 Extracted relevant data from PDF using regular expression in python

 Used Google API key to extract information of hospitals all over the world

 Shortlisted relevant topic from news websites using topic modeling

 Helped our client in getting new leads by targeting news articles and websites

 Developed a classification model to analyze win loss opportunity leads with the accuracy of 94% Analyst: Tata Consultancy Services– Bangalore, Karnataka 03/2019 to 09/2019

 Data Manipulation/Cleaning of CSV, Excel, using Python

 Data Analysis using Pandas (Python) with Regular Expression

 Identified trends, patterns and relevant information from given data using statistical/machine learning

 techniques to provide data driven solution

 Created a data ingestion pipeline application to execute data pre-processing steps with configurable rules

 Analyzed Aircraft's fuel efficiency and improvised it using machine learning algorithms

 Predicted engine failure using classification model to minimize possible damage