Sudhir Rai

Data Analyst | Business Intelligence | Data Engineer

Over the years, I’ve had the opportunity to work on a number of incredible projects that have allowed me to grow and establish myself within this competitive industry. I hope you’ll enjoy viewing my projects as much as I enjoyed working on them.

Professional History

Data Analyst

Internship

Primus Global Services Inc
July 2019 - November 2019

Configured cloud watch dashboards, billing alarms and performance alarms to monitor using AWS QuickSight
Grouped resources and organized the billing dashboards to understand cost vs usage by customers using AWS QuickSight
Organized the IAM for the team and set up roles with granular permissions
Architected railcar file handler flow that sends a notification to a lambda function when a file is uploaded to S3 and push that data to multiple data stores
Developed a tool which capture images and gives the total count of railcar present at given point of time.

Associate Consultant

Data Analyst

Capgemini
August 2016 - July 2018

Transformed and cleansed unstructured financial data using Python to conform to the business requirement of HSBC bank
Performed the ETL process for data cleansing and data modelling by using SAP Hana to create cubes and views.
Developed dynamic and interactive dashboards in Power BI to provide tracking of key financial performance indicators
Automated the time frame to reflect the updated balance which increased customer transaction by 10%.

Software Engineer-

Data Analyst

Wipro Technology
January 2014 - August 2016

Analyzed transactional data collected over different regions, Data cleaning, modelling and filtering done using Python for CITI
Visualized financial data using Tableau and increased the revenue by 2.7% by decrease in fraud TPIN transaction
Developed the dashboard to present type of transaction causing the fraud and factors contributing in increase in revenue.
Encrypted Telephone PIN using IBM encryption technique in legacy system to increase the privacy and created a report using SQL Query view for tracking the performance of the system.

Home: CV

My Work

House Prices: Advanced Regression Techniques

Used both python and R for this. Data imputation was done using pandas

Scikit-Learn was used to train advanced regression like Random Forests and XGBoost and Random Forests to predict House Prices using Advanced Regression techniques

The best R2 obtained for the models was 0.85

Data Visualization Impact of refinery in states

Analyzed the pattern of oil refinery and disaster in states and the impact of disaster over the refinery present in the states

Integrated Data analysis with R in tableau, for creating decision trees and K-mean clustering analysis

Created visually impactful dashboards in Tableau for data reporting

Predict Customer lifetime value

Performed predictive analysis on the customer data (Watson Analytics- Marketing Customer Value) to predict the most profitable customers by performing regression using SAS E-miner

Resulted in retaining the most valuable customer to increase the revenue of the company

Analysis of Texas weather

Extracted 1864 weather data from Texas weather using BeautifulSoup and stored in csv file. Transformed and cleansed using Alteryx

Visualized the weather pattern, wind speed all over Texas, top 5 cities with highest temperature and max and min temperature in Tableau

Integrated Analysis on Titanic Dataset

Applied Logistic regression, built decision tree and implemented K-mean clustering in R studio

Integrated R model and Tableau using RServe() and visualized results to ensure the best chance of survivability

Sentiment Analysis of Twitter feed for IPad Pro and Surface Pro 4

Performed Text and Sentiment Analysis for iPad Pro and Microsoft Surface Pro 4 using SAP HANA twitter API

Extracted, interpreted and analyzed data to identify key metrics and transform raw data into meaningful, actionable information

Visualized the finding using SAP Lumira

Home: List