RISHABH TANEJA

Boston, MA 857-***-**** adhak7@r.postjobfree.com https://www.rishabhtaneja.com/ https://www.linkedin.com/in/rishabh-taneja/

EDUCATION

Northeastern University, Boston September 2018 – March 2020

Masters in Analytics with a concentration in Statistical Modeling GPA: 3.87/4

SRM Institute of Science and Technology, Chennai July 2014 – June 2018

Bachelor of Technology – Computer Science and Engineering GPA: 3.52/4

WORK EXPERIENCE

Northeastern University, Data Analytics Research Assistant May 2020 – Present

Research focused on COVID-19, its spread and how states reacted to it to provide better recommendations for future decisions

Prepares summaries of data collected through multiple sites via automation and contributes to the evaluation and discussion of results related to COVID-19

Northeastern University, Graduate Teaching Assistant January 2020 – March 2020

Designed and facilitated customized study sessions for 60 students for probability and statistics course before each submission. Also evaluated student performance and provided direction for improvement

Received an appreciation and recommendation letter from management and the assigned professor for teaching excellence and time-management

AAKRITI, BI Data Analyst Intern June 2017 – August 2017

Produced a report on trend analysis after extracting and cleaning the data of production and manufacturing of cement using R which was ultimately connected to the database operating MySQL

Optimized data view that enhanced the overall performance by 15% with the creation of real-time dashboards utilizing R Shiny and Power BI on the data imported from Google Analytics

Shishodia Realtors Builders and Developers, Data Analyst Intern December 2016 – January 2017

Created formulas in Microsoft Excel spreadsheets, deployed pivot charts and utilized the specialized data from the company’s sales team to calculate the increase in sales

Visualized data anomalies in Tableau and designed a dashboard to optimize trivial tasks, reducing man-hours by 60% utilizing the company’s sales data

Collaborated with the logistics team in improving order assigning algorithms and reduced unaccepted deliveries by 73%

SKILLS

Programming Languages: Python, R, HTML5, CSS3, Git, R Shiny, SQL, NoSQL

Machine learning: TensorFlow, Keras, Sklearn, Google Analytics, A/B Testing

Technologies: AWS, CLS, Google Survey, Excel, PowerPoint, Tableau, Power BI, SAS, SPSS, ETL, SAP, Oracle Database

PROJECTS

CAPSTONE- Analyzing factors affecting employee productivity, Enaible Inc – (Python, Tableau, MySQL)

Performed EDA and feature engineering to establish a correlation between the most suitable factors for the model

Drove the solution by introducing 2 new attributes to improve the emp productivity score by 45%, beating the average by 0.2

Developed a framework/machine learning workflow to better understand the calculations behind the productivity score

Analysis of student move-in issues using AWS – (Lambda, s3, Quicksight, Athena, Glue, boto3, Rekognition, NoSQL)

Deployed an AWS cloud infrastructure/model responsible for extracting and collecting the data to process the

images of items on the streets using Object Detection API

Segregated every item into its parent category directly helping us identify the recyclable items out of the lot using Quicksight

Sentiment Analysis using N-gram and Naïve Bayes – (Python, R, TensorFlow, Data Mining, Tagging, Parsing)

Analyzed sentiments, performed tagging and syntactic parsing via natural language processing of 3 different files of text data about reviews collected from 3 different sources using e1071.

Executed N-gram analysis to find the correlation between words. Implemented Naïve Bayes classifier to classify reviews into positive or negative sentiment with final accuracy 74%, precision 66%, recall 80% using cross-table for predicted vs actual

Price Prediction in real estate – (Python, Jupyter Notebook, pandas, NumPy, matplotlib, sklearn, ETL)

Performed feature engineering to choose relevant features having an impact on our label, price

Created a pipeline to automate tasks such as imputation and standardization and performed model selection using sklearn

Evaluated Random Forest Model and concluded it to be the best performing model with least root mean squared error as 4.25

Contact this candidate