Skip to main content

Sankalp Chauhan (He/him)


Currently living in

Wayne, New Jersey, US

Work Preferences


Open to roles

Short Term ContractLong Term Employee

I graduated from Rensselaer Polytechnic Institute (RPI) as a summa cum laude majoring in operations research math and I have a lot of experience in data science. I interned at Simons Foundation and worked at BPK Tech.

Ideal Workplace Values

Friendly, Teamwork motivated, Inclusive

My Badges

Skills and Strengths

My Neuro-exceptional talent

My neurodiversity gives me the advantage of being detail-oriented. I like to focus on the nitty-gritty of tasks that other people find tedious.

Technical Skills

Top 5 Soft Skills

CollaborationActive ListeningWorking AutonomouslyReliabilityAttention to Detail

Inclusion Essentials


Send Questions in AdvanceAccessible BuildingInterviewer Experienced with NeurodiversityExtra TimeWritten interview instructionsConcise InstructionsUninterrupted Work TimeCounselingJob CoachingSupport Group for StressTherapy

Environments I'm comfortable with

Heavy lifting
Loud noises
Outdoors or places with strong smells
Standing for long periods
Variable temperatures
Uniforms (hard hat, hair net, etc.)
Working with animals
Driving a vehicle
Working with food
Interaction with the public
Bright or blinking lights


Check out my work

Working since Nov 2021

Data Analyst - BPK Tech

Created a predictive model from scratch examining the data of rejected dental insurance claims to determine future rejection/acceptance using R and SQL • Connected SQL table data to Python to run random forest algorithm, created dummy data in Excel to determine model functionality in real-time • Divided the real data set into testing and training to determine model accuracy, achieved 99% predictive accuracy

PythonMicrosoft SQL ServerRSASJulia
Working since Oct 2021

Internet Marketing Specialists - BPK Tech

I looked at rejected dental claims data and found wherein the data corresponded with the rejected claim. Then I used a RandomForest machine learning model on the claims data and got 99% accuracy. Afterward, I created my dummy data in Microsoft Excel. Then I used my RandomForest model to predict the probability of each claim getting Rejected or Not Rejected.

PythonMicrosoft SQL ServerR programmingdata analysismachine learning
Worked for 7 months from Feb 2021 to Sep 2021

Data Analyst - Simons Foundation

Coded a Q&A machine from scratch in Python and Natural Language Processing (NLP) to enhance user experience on the foundation’s FAQ page • Utilized Juypter Notebook and Google Colab to create a machine that increased user-friendliness and the ease of finding information about the foundation’s autism research • Created Tableau visualizations of autism research data after converting files from JSON to CSV format for easier use

PythonTableauNLPJuypterGoogle Colab
Worked for 11 months from Oct 2020 to Aug 2021

undefined - University of Texas Rio Grande Valley

• Analyzed change in computer sensor data using Inverse Reinforcement Learning (IRL) to develop algorithms to reconfigure and personalize web content to the user’s habits and activities • Co-authored “Inverse Reinforcement Learning: an application in distinguishing mouse cursor movement” detailing my contribution to the project • Implemented IRL and Deep IRL functionalities to model individual and population-level behavior analysis

PythonLinuxLaTeXReverse reinforcement learningDeep inverse reinforcement learning
Worked for 5 months from Jan 2020 to May 2020

undefined - Rensselaer Polytechnic Institute, Cognitive and Immersive Systems Lab (CISL)

I developed an iterative feedback generation model and phenome recognition algorithm for a chatbot to discern IPA (International Phonetic Alphabet) sequences between native and non-native Chinese speakers I used the Machine Learning and Neuronal perspectives of reinforcement learning to train a teaching chatbot to correct language pronunciation and provide needed (most rewarded) feedback to students. I designed a user simulator that completes an error assessment based on the difference between the "detected" IPA categories and "target" IPA categories and implements a detection system to correct human errors

PythonChatbot DevelopmentIPAAlgorithmsReinforcement Learning

Education and Credentials

Attended for 4 years from 2016 to 2020

Rensselaer Polytechnic Institute

Bachelor's degree - Applied Mathematics