• Hi!
    I’m Kshitij

    A Data Professional executing data-driven decisions to drive business growth.

About Me

Who Am I?

Hi! I’m Kshitij Sankesara, a Data Science professional with a background in Engineering. I have pursued a Masters in Data Science from Syracuse University and a Bachelor’s in Industrial Engineering from the University of Mumbai.

I am currently working on reinventing analytics and growing Lilt. I leverage data and help services, revenue, and operations team to make data-driven decisions. I handle the company's product and financial data and perform analytics and reporting to create business value.

I am highly skilled in turning data into information and information into insights for businesses. My passion is to leverage my skills to help organizations drive decisions through a solid data-driven approach.

My Achievements:

Analytics at Lilt

M.S. in Data Science with 3.9/4.0 GPA

Graduate Teaching Assistant mentoring 100+ students in multiple Data Science courses at Harvard, Syracuse, and Hult University

Leading Team of Data Analysts

GitHub with 40 repositories of multiple DS and ML projects

Tableau Public Profile with 10+ interactive Dashboards

Here are some of my expertise

Data Analytics

Analyzing data to get insights and helping businesses in data-driven decision making

Data Engineering

Connecting multiple data sources and Managing data pipelines, workflows, and ETL processes

Statistical Analysis

Leveraging statistical techniques to understand the data and extract business insights

Data Reporting & Visualization

Creating interactive reports and dashboards to help make informed data decisions

Machine Learning & Deep Learning

Building algorithms to identify trends and patterns and reduce human error

Business Knowledge

Leveraging data to help stakeholders make data-driven business decisions

My Skillset

Programming Languages:

SQL, Python, R

Visualization Tools:

Tableau, Power BI, Quicksight, Looker, Google Data Studio, Qlik

Database:

SQL Server (SSIS, SSRS, SSAS), Amazon Redshift, PostgreSQL, Google BigQuery, MySQL, MS Access

Tools & Techniques:

MS Excel, Spark, MapReduce, Alteryx, Databricks, SPSS, Google Analytics, Adobe Analytics, A/B Testing

Python Libraries:

Pandas, NumPy, PySpark, Scikit-Learn, TensorFlow, Keras, XGBoost, Matplotlib, Seaborn, Plotly

Machine Learning Models:

Regression - Linear, Logistic, Multiple, Ridge, Lasso
Classification - KNN, Decision Trees, Random Forest, Naive Bayes, SVM
Clustering - K Means, Hierarchical, Mean Shift
Deep Learning - Multilayer Perceptrons, CNN, RNN, LSTM
Time-Series - Univariate, MultiVariate

Education

My Academic Journey

Syracuse University
GPA: 3.9 / 4.0

Aug 18 - May 20

Related Coursework:
Data Analytics, Data Visualization, Data Reporting, Data Warehouse, Database Management, Big Data, Business Analytics, Statistical Analysis, Machine Learning, Deep Learning, NLP, Text Mining, Decision Making, Financial Analytics

Work Experience

My Professional Journey

Data Analyst at Lilt Dec 2020 - Present

Data Scientist at OnPoint Insights May 2020 - Nov 2020

Graduate Assistant and Tutor at Harvard University, Hult University, and 2U Aug 2020 - May 2021

Lead Data Analyst at Syracuse University Aug 2019 - Apr 2020

Graduate Teaching Assistant at Syracuse University Aug 2019 - Apr 2020

Data Analyst Intern at Bizlitics LLC June 2019 - Aug 2019

Data Analyst at Larsen & Toubro June 2017 - Dec 2017

My Work

Data Science Projects

To learn new tools and techniques and to improve my Data Science skills, I have completed 35+ projects and have shared my code on GitHub. I have also developed multiple interactive Dashboards to hone my Data Visualization skills using various BI tools.

Data Warehouse Integration

Project Link

  • Pull data from multiple sources and integrate data into database using data pipelines, ETL processes, and SQL queries
  • Manipulate data to interpret large datasets and visualize data using business intelligence tools for generating insights
    • Tools: SQL, SQL Server, ETL, SSIS, Microsoft Excel, Power BI

    Predicting Loan Defaulters and Interest Rate

    Project Link

  •  Clean data of 2.2 million rows and 151 columns and use linear regression for prediction with error rate of less than 2%
  • Build model pipelines using Pyspark for implementing logistic regression and random forest models for classification
    •  Tools: Python (Pandas, Numpy, Pyspark, Matplotlib, Seaborn), ML Models (Linear Regression, Decision Tree Regressor, Logistic Regression, Random Forest)

    Describing and Forecasting Flight Delays

    Project Link

  • Merge and transform large data sets of 6 million+ records and perform feature engineering and exploratory data analysis
  • Use time series analysis to predict delays and regression analysis with R2 of 0.94 to understand significant relationships
    • Tools: MS Excel, ML Models (Linear Regression, Logistic Regression, Multiple Regression, Time-Series Forecasting)

    Sentence Detection using Deep Learning

    Project Link

  • Research and develop algorithm for processing unstructured data using NLP techniques with accuracy of 98.5%
  •  Train multiple Neural Networks on 1 million+ text data and compare them based on accuracy, size of data, and time taken
  • Delivered an Open-source platform which provides solutions based on reports generated from data querying
    • Tools: Python (Tensorflow, Tensorboard, Numpy, NLTK), Deep Learning Models (ANN, CNN, RNN, LSTM)

    Analyzing Financial Risks of Stock Market

    Project Link

  • Perform descriptive analysis and summary statistics on stock prices of multiple companies for over 5 years
  • Develop visualizations, time-series forecasting, and regression analysis to analyze risk associated with each company’s stocks
    • Tools: R (ggplot), Time-Series Forecasting, Regression Analysis

    Analyzing Black Friday Sales

    Project Link

  • Analyze sales data of 538k records by performing data preprocessing and descriptive analysis  
  • Build and compare ML models like Regression, SVM, Naive Bayes, and Random Forest to understand customer behavior with 60% accuracy
    • Tools: Python (Numpy, Pandas, Sklearn, Matplotlib), ML Models (Linear Regression, SVM, Naive Bayes, Random Forest)
    My Journey of Recognition

    Leadership

    Data Science Mentor Harvard University

    Data Analyst Project Lead Syracuse University

    Graduate Teaching Assistant Syracuse University

    Student Supervisor Sadler Dining Hall

    Volunteer Nanhi Kali

    Finance Committee Member Graduate Student Organization

    Get in Touch

    Want to get in touch? I'd love to hear from you. Here's how you can reach me..

    kshitij.sankesara@gmail.com

    +1 (315) 679-9604

    Kshitij Sankesara

    GitHub: kshitijsankesara