Data Scientist Software Development

Saurabh Kankekar

650-***-**** *****************@*****.*** Linkedin Github

PROFILE

Aspiring Data Scientist and Master's candidate in Business Analytics with experience as a Consultant specializing in Software Development Lifecycle (SDLC). Developed and improved organizational processes, enhancing operational efficiency for over 170,000 users. Implemented complex data integrations to streamline workflows, resulting in smooth system functionality. Led a technical team to achieve a flawless issue resolution rate through strategic project leadership and data analysis. Aims to leverage analytical expertise and leadership to support data-driven solutions and model development in a Data analytics role.

PROFESSIONAL EXPERIENCE

Data Scientist - Fashom (Practicum) San Francisco, CA Aug. 2024 - Jun. 2025

• Built a recommendation system using collaborative filtering in Python, leveraging shopping data to boost purchase rates by 14%

• Conducted A/B testing on the recommendation engine, achieving a 19% lift in engagement and a 12% increase in conversion rates

• Analyzed repeat customers, identifying younger customers preferring brighter casual wear, enabling targeted marketing strategies

• Created ERD diagrams between key database tables, increasing data retrieval optimization for the recommendation system by 22%

Consultant - Deloitte Mumbai, India Aug. 2021 - Jul. 2024

• Served as the technical lead in developing the Leave of Absence (LOA) process area, incorporating data modeling and analysis techniques to enhance process efficiency and scalability for 170,000 employees.

• Implemented five complex integrations with third-party tools using data engineering best practices, streamlining workflows, enhancing operational efficiency, and aiding model deployment activities.

• Parsed and managed diverse datasets utilizing SQL and Python, ensuring data validation and accurate system functionality through effective data mining techniques.

• Led a team of seven, conducting daily scrums and achieving a 100% issue resolution rate through rigorous data validation and testing strategies.

• Designed and managed reports and dashboards by analyzing data with statistical methods, delivering actionable insights to support data-driven decision-making for key stakeholders. PROJECTS

Yeast Gene Expression – Titer Prediction Modeling Github Apr. 2025

• Modeled synthetic protein titer using gene expression data from UCI Yeast dataset, simulating a fermentation R&D use case.

• Applied EDA, feature engineering, and transformations (e.g., log-transform on mit, nuc) to prepare biologically realistic inputs.

• Trained Linear Regression and Random Forest models (R : 0.785 and 0.742), evaluating predictive signal across features

Credit Risk Classification Github Feb. 2025

• Developed ML models (Logistic Regression, Random Forest, XGBoost) to predict creditworthiness.

• Achieved 0.76 AUC by tuning hyperparameters and applying cross-validation.

• Created ICE plots to interpret feature influence and ensure model transparency. Twitter Data Pipeline with Airflow and AWS Dec. 2024

• Built a Twitter data pipeline using Airflow, Tweepy, and AWS S3 to extract, process, and store data, leveraging Python and Pandas for ETL workflows.

SKILLS

SQL, Oracle SQL, SQL Server, Tableau, R, Python(NumPy,Pandas, Scikit-learn, Matplotlib), AWS Redshift, Netezza, MS Excel, Collibra, Jenkins, JIRA, Confluence, Power BI, MongoDB, Git, Web Scraping (Selenium), MS Visio, Data Warehou sing & Modelling, ETL, Data Analysis & Visualization, Data Wrangling, Data Storytelling, Predictive Analytics Machine Learning and Statistical Techniques: Decision Trees, Random Forest, Support Vector Machines, XGBoost, Neural Networks, Regression (Logistic, Lasso, Ridge, Elastic Net), ANOVA, Principal Component Analysis, A/B testing Certifications: CSA, CAD

EDUCATION

Master of Science, Business - Analytics, University of California, Davis United States Aug. 2024 - Aug. 2025 Master of Computer Science - D.G Ruparel College India Aug. 2018 - Oct. 2020

Contact this candidate