Anshul Dabas

Data Scientist, Machine Learning Engineer, & Analytics Enthusiast | Driving Customer-Product Engagement Growth Across 1M Users

Xilinx 0.2 Yrs , TrustedCare Holdings, Inc. (Prof. Bruce Harmon) 0.4 Yrs , monocept 0.6 Yrs , 1.0 Yrs

University of Denver, USA Master of Science Data Science, NIT- Calicut, India Masters Computer Applications, University of Delhi, India Bachelor of Arts Mathematics & Economics

Data Scientist 00.06 Yrs, Machine Learning Engineer 00.06 Yrs, Data analyst 00.06 Yrs,

SQL,  Python,  Machine Learning,  Data Analysis,  Predictive Modelling

About Anshul Dabas

Mathematics and coding are two languages I am most fluent in. Even back in my high school, I used to be most enthusiastic about the C++ class and mathematics class.In line with my interest, I majored in Mathematics in my undergraduate degree and chose to study Computer Applications in my Master’s.

Every real-world problem is a challenge I like to take on.My constant quest has been to bridge the gap between the digital and the real. I designed and launched a Scholarship Management (a web application) for my graduate school. This platform automated all the processes and helped the school go paperless.

As a software developer, I have worked on NodeJS, MongoDB, AWS for over two years. During this time, I got to work closely alongside data-analysts. That experience inspired me to explore the science behind data to research solutions that will impact the business via data-driven approach and techniques.

Data science seemed to me to be the perfect intersection of all things I have been passionate about: mathematics, data, problem-solving, and business skills. I decided to study Data Science comprehensively. I completed my MS in Data Science with a GPA of 4.0. I worked on more than 10 data science and machine learning academics projects during my course of study.

As an intern with Xilinx I mined the customer behaviour of close to a million users through ML algorithms and devised business strategies to boost user engagement for the firm. This was a wholesome experience. I developed a keen understanding of customer behaviour and engagement activities to develop innovative products/ services by leveraging Data Science.

I am looking for full time opportunities where I can continue using data science to drive business and keep exploring the vast possibilities that data withholds.

Skill Set: Python, SQL, R, Prediction Modelling, Databricks, MongoDB NLP, Machine Learning, Neural Networks,Hypothesis Testing,Advanced Analytics,Power BI, Google Analytics, Tableau,Probability & Statistics in Data Science,Sentimental Analysis,Data Mining & Pattern Recognition.

Total Work Experience: 02. Yrs

Domain Experience : Insurance domain,Health care domain,Artificial Intelligence Domain,Semi-Conductor Domain,E-commerce Domain,Supply Chain Domain

Work Sponsorhip/Visa Required? : Yes, F1


  • SQL
  • Python
  • Machine Learning
  • Data Analysis
  • Predictive Modelling


  • Communication
  • Agile Development
  • Business Strategy & Solutions
  • Data Story Telling
  • Leadership
  • Teamwork
  • Problem Solving
  • Spark
  • AWS
  • MySQL
  • Mongo DB
  • MEAN Stack
  • Linux
  • Node.JS
  • Plotly,Power BI,Bokeh,python,Jupyter Notebooks,Tableau,Google Analytics


  • Data Scientist 00.06 Yrs
  • Machine Learning Engineer 00.06 Yrs
  • Data analyst 00.06 Yrs


Company Name: Xilinx

Job Title: Data Analyst Intern

Experience: 2020 Jun - 2020 Aug (0yr 2mos )

• CX-optimization on ~250K users with predictive models using supervised (regressions) & unsupervised (K-means) ML algorithms

• 90% efficiency in customers’ survey evaluation process by automating via LDA text mining algorithm to extract majority feedback

• Prototype ML models by researching via EDA on customer data (Google Analytics, Power BI, Python, SQL, MS Access)

• 80% lift in customer data extraction time by using API calls instead of multiple database transactions

• Independently led the project from end-to-end (research to data-driven Insights to predictive analytics to business strategies)

• Data-driven business solutions presented via data story telling approach to key stakeholders (both technical & non-technical)

Company Name: TrustedCare Holdings, Inc. (Prof. Bruce Harmon)

Job Title: Data Analytics(Student Consultant)

Experience: 2020 Sep - 2021 Jan (0yr 4mos )

• Co-morbidity analysis and research on 500 patients by using their health scores and claims historical data (Python)

• Visualize patterns of 4 co-morbidities simultaneously to study variations in heath score fluctuations & develop insights

• Present business solutions to the CEO as time series ML models - Dynamic Time wrapping and CNN to predict diseases correlation

Company Name: monocept

Job Title: Software Engineer

Experience: 2018 Jun - 2018 Dec (0yr 6mos )

• End-to-end data architecture implementation for ~4K customers worth ~$1M by using NodeJS, MongoDb & AWS

• Cloud-computing transformation by developing app that contributed to 17% revenue growth for the client (MaxLife Insurance)

• Analyzed implementations & solutions on backend data with Business Analysts to optimize customer experience

• AWS Redis Cache integration with the app to increase time efficiency of database transactions by 80%

• Led a team of 6 members for Product Configuration & Development to analyze, transform and design product mappings data

from distributed database systems and microservice architecture for REST APIs

Company Name:

Job Title: Software Developer

Experience: 2017 Jan - 2018 Jan (1yr 0mo )

• Develop data retrieval solutions for 5K customers by using NodeJS, MongoDB & AWS

• Customer Dashboard development by using ETL on orders, credit, invoice, shipping & payment data

• Evaluate customers’ engagement on ecommerce platform while brainstorming alongside Business & Data Analysts

• $200K worth B2B supply chain process automation by leveraging cloud platform app development

• Led development of customer & credit module, from end-to-end database architecture implementation to app functionalities

Academic Projects

Title : Product Recommendation System & Customer Behavioural Analysis
Technology Used : Python, Machine Learning, Data Analysis

Analyzed and modelled customers into different groups using Clustering based on their platform activities and behavior.

Applied Pattern Recognition techniques like – Apriori Algorithm (based on Association Rules) and Utility Correlation Matrices to find similar products and customers.

Title : Predict Austin’s Animal Shelter Adoptions
Technology Used : Python, Exploratory Data Analysis, Prediction Modelling

Predicted early successful adoptions & effective contributing features by comparing the results from Logistic Regression, KNN and Decision Trees. Also, achieved an increased accuracy via Gaussian Naïve Bayes Classification and feature engineering techniques from ~63% to 76%

Title : Amazon Product Reviews’ Sentiment Prediction
Technology Used : Python, Exploratory Data Analysis, Prediction Modelling

Published an app on PythonAnywhere platform to predict sentiment of a review with simultaneous feedback learning via NLP, Logistic Regression, SGD classifier and cross validation

Title : Predict BMI Class Using Streaming Data Simulation
Technology Used : Spark, Databricks, Machine Learning

Applied distributed computing in databricks AWS cluster by using spark on streaming data via pipelining Logistic Regression model to predict BMI class for a person

Title : World View and Happiness
Technology Used : R, Rstudio, Propensity Modelling

Researched if we could predict happiness score of a nation based on its citizens’ survey that included their perspective about their society (economy, equality, religion etc.) by implementing XGBoost in R

Title : Image Classifier App
Technology Used : Python, Neural Networks

Project descriptionBuilt a neural network model to classify car vs airplane images by using keras (TensorFlow) and improved the accuracy from 53% to 83% specifically via hyperparameter tuning

Title : CO2 Emissions Analysis
Technology Used : R, Rstudio, Prediction Modelling

Predicted increase or decrease in CO2 emissions for a country during 2001-2014 given their renewable energy consumption, forest area and urban population by applying Logistic Regression in R


, Data Science

, Computer Applications

, Mathematics & Economics