Hi, I'm Abhishek

and I am a passionate

About Me

My Introduction

Data Engineer & Data Scientist with extensive work experience using domain tech-stracks.
With a Master's in Business Intelligence & Analytics from Stevens Institute of Technology, I specialize in data science. With proficiency in Python, R, Java, C, C++ and SQL, I excel in end-to-end development.

3+ Years Experience
Completed

5+ Projects Completed
Written

2 Companies Worked
Papers

Download Resume

Skills

My Technical Level

Python

90%

Java

80%

PySpark

75%

R

70%

C++

40%

MS Excel

80%

NumPy

80%

pandas

90%

matplotlib

70%

scikit-learn

85%

Pytorch

85%

OpenCV

65%

NLTK

60%

streamlit

80%

seaborn

70%

Flask

40%

Linear and Logistic Regression

95%

Decision Trees

95%

Ensemble Models

90%

Clustering

65%

Convolutional Neural Networks

80%

Graph Neural Networks

60%

Recommender Systems

75%

Natural Language Processing

65%

Exploratory Data Analysis

90%

Multi-modal Learning

70%

Time Series

55%

AWS Sagemaker

65%

AWS EMR

75%

AWS Lambda

70%

Big Query

40%

Docker

60%

Apache Airflow

40%

Kafka

40%

MySQL

85%

IBM Cognos

75%

Qlikview

70%

Tableau

50%

Power BI

50%

Qualification

My Personal Journey

Education

Work

Masters of Science in Business Intelligence and Analytics

Stevens Institute of Technology, NJ, USA

2023-2024

B.Tech in Electronics & Telecommunication

K.J.Somaiya College of Engineering, Mumbai, India

2016-2020

Business Intelligence Analyst

eClinicalWorks

January 2025 - Present

Developed OLS Multiple Linear Regression model, which helped in understanding the statistical significance of variables such as patient & provider demographics on edit rates. Developed the model for 5500 encounters and 30 providers.

Business Intelligence Intern

eClinicalWorks

June 2024 - December 2024

Performed statistical analysis for 3 different clients, analyzing the encounter counts, time spent on progress notes per encounter, total time spent off-hours, time to lock progress notes, SOAP analysis for off-hours & working hours, and total EHR time per appointment.
Helped with optimising the SQL query in IBM Cognos Query Studio, enhancing the report execution time by 20%.
Tested 28 different UDS reports by creating 100+ patients, according to new HRSA requirements.

Data Engineer

Accenture

July 2022 - July 2023

Worked on process enhancements and created multiple analytical dashboards for clients highlighting financial trends saving up to 77% of the effort spent during manual analysis.
Developed multiple automations using Python, which helped in a significant reduction in manual efforts.
Collaborated with multiple cross-functional teams and clients regarding incidents and process improvements.
Maintained above 95% success rate in meeting Service Level Agreements across applications.

Application Developer Associate

Accenture

December 2020 - June 2022

Monitored, developed and maintained Batch data pipeline with the help of CA Workload Automation software. Troubleshooted production failures using linux and Ab Initio.
Ran MYSQL and Oracle queries to gain insights into the data and presenting it to client in a very clear and concise manner.
Refactored the existing host extraction code in Ab-initio which helped team to save time in their activities. Tested the code with other dependent jobs and then migrated the code to production environment.
Responsible for monitoring, supporting and analysing ~1000 executions of ~60 jobs on monthly basis.
Received Commitment to Excellence Award in my first year.

Portfolio

My Projects

Sign Language to Text using CNN

Using CNN and OpenCV converted the american sign language to text. This project helps deaf people understand and communicate effectively.

View Code

Data Science Salary Estimator

Using BeautifulSoup, extracted data from glassdoor. Pre-processed, analysed, and predicted various Data Science roles salaries across USA.

View Code

Movie Recommendation

Developed recommendation model using collaborative filtering and content based filtering algorithms. The model recommends top 5 movies according to user's items and contents.

View Code

Recommendation & Price Prediction for used cars

Developed recommendation model using TF-IDF to recommend used cars and modeled Linear Regression, Logistic Refression and Random Forest classifier to predict the price.

View Code

Stock Price Analysis

Used Kafka to stream data from producer to consumers. Analyzed data on consumer end and used Efficient Frontier to maximise returns using max-sharpe ratio.

View Code