Sneha Sankar
Computer Science at University of York
Work by Sneha Sankar
- Acquisition Analysis of VLBTech by SustainVolt
Conducted an evidence-based consultancy analysis evaluating SustainVolt’s potential acquisition of VLBTech to expand renewable energy capabilities. Assessed market opportunity, financing options, risks, and assumptions to support strategic investment decision-making. Applied McKinsey’s 7S framework…
- Microsoft Office Specialist Excel
Achieved a perfect score in Microsoft Office Specialist Excel.
- Predictive Analytics and MCDA for Business Optimization
This business analytics project contains two parts. In Part one, customer spending is predicted using he CRISP-DM framework and linear regression. In Part Two, MCDA is applied. TOPSIS is used to rank and select the best delivery robot based on multiple criteria.
- Will Your ICO Succeed Predicting ICO Fundraising Success Using Machine Learning Models
This project applies machine learning models to predict the success of Initial Coin Offering (ICO) fundraising. Multiple models—Logistic Regression, Decision Tree, Random Forest, and XGBoost—are trained and evaluated. Performance is assessed using metrics like accuracy, precision, and F1 score.
- Universal Export Data-Driven Visualisation for Business Intelligence
This project focuses on using data visualization for business intelligence. The first part targets shareholders with high-level company insights. The second part analyzes personnel performance, demographics, and compensation. The final section explains the storytelling approach behind the…
- Advanced Forecasting and Text Analytics for Business Strategy
This project combines forecasting and text analytics to support business strategy. The first part focuses on predicting Personal Consumption Expenditures (PCE) using time series models. The second part analyzes hotel reviews with text mining and topic modeling to uncover key drivers of customer…
- Urban Road Traffic Accidents Predicting Risk Patterns in Manchester and Birmingham
First comparative cross city study in the field of traffic accident prediction in UK using multi-source data. Applied spatio-temporal analytics, network modeling, and machine learning techniques.