Profile Image

I'm Shashank Rotti Data Scientist at Cornerstone Research

Work Experience

  • Cornerstone Research Data Scientist
  • Bank Of America Application Architect V
  • Trade Terminal Quantitative Researcher
  • Deloitte Technical Analyst | Technical Consultant

Education

  • New York University Masters in Financial Engineering
  • PES University, India B.E in Computer Science

About Me

I am a Master's in Financial Engineering graduate from NYU and currently work as a Data Scientist at Cornerstone Research, specializing in Market Microstructure and FinTech projects. I am passionate about bridging the gap between Quantitative Finance and Data Science, striving to develop effective and robust solutions to complex business challenges.

With a strong foundation in Capital Markets, Engineering, and Technology, I thrive on building projects from scratch or gaining a comprehensive understanding of existing ones to contribute innovative ideas. My deep interest in solving mathematical problems and creating tangible results has driven my exploration into the dynamic world of Quantitative Finance and Data Science.

I am particularly focused on Predictive Modeling, Quantitative Research & Analysis, Machine Learning, Risk Analytics, and Statistical Modeling. Proficient in multiple programming languages, including Python, SQL, C/C++, and Java, I excel at converting business problems into technical solutions and transforming raw data into actionable insights.

As a CFA Level 2 candidate, I am committed to advancing my expertise in financial analysis and investment management, further complementing my technical skills. My goal is to leverage cutting-edge analytics and technology to create meaningful impact in the financial industry.

Download Resume

Core Skills

  • Python
  • R
  • C++
  • MATLAB
  • SQL
  • Linux
  • Sklearn
  • Pandas
  • Numpy
  • Tensorflow
  • Excel

Other Skills

  • Regression
  • NLP
  • Forecasting
  • Statistical Modelling
  • Time Series Analysis
  • Machine Learning
  • Deep Learning
  • Quantitative Analysis
  • Financial Modeling
  • Portfolio Management
  • Risk Management
  • Trading Strategies
  • Git

Work Experience

2018 - 2022

Deloitte

Technical Consultant, Technical Analyst
  • Developed a data lake architecture on AWS, using Python for ETL and AWS Glue for data management. Transitioned claims data from legacy databases to AWS S3, enhancing analytics and saving $65M annually.
  • Built a customized data visualization tool using Python and Tableau to integrate data from multiple vendors' data science infrastructure, enabling validation, data profiling, and achieving a 30% reduction in processing time.
  • Worked in an agile software development environment to identify and rectify critical payment flow functionality issues for a client, saving $50M in annual revenue leakage.
May to August 2023

Bloomberg

Quantitative Researcher - Industry Capstone: Thematic Investment using NLP
  • Designed & refined methodologies for thematic identification, using NLP techniques including Semantic Embedding, Named Entity Recognition, Topic Modelling & Text Classification.
  • Leveraged supply chain overlap to calculate theme related exposure score for companies; achieved 94% precision & enhanced the granularity of thematic identification.
Jan 2024 - May 2024

Trade Terminal

Quantitative Researcher Intern
  • Implemented a market-making strategy from concept to execution using modular Python code, integrating real-time order updates via WebSocket and REST API for custom order management, resulting in a 2% profit increase and a portfolio activity ratio of 56.
  • Conducted research and implemented an autoregressive distributed lag logistic regression model to improve the hit rate of lead-lag arbitrage strategies by 5%, thereby boosting profitability by better spread capture.
  • Developed Python scripts for data aggregation and processing from Influx DB, Prometheus, and MongoDB, enabling real-time visualization of risk metrics on Grafana, which enhanced portfolio risk management efficiency by 50%.
  • Developed a statistical arbitrage strategy using Order flow imbalance, achieving 40% CAGR with a maximum drawdown of 2.8% in backtesting; currently optimizing order execution for seamless performance.

Latest works

Assesment of Earnings Release on Stock Price Movement

Built a stock analysis tool in C++, retrieved stock data using Libcurl API, analyzed stock movement after earnings date announcement, and used Gnuplot for visualization.

Github

Trading Strategies

Designed & Implemented Trading Strategies like Pairs Trading & Market-Neutral Momentum Crashes Strategy.

Github

Active Portfolio Management using Machine Learning

Built a portfolio optimization model, using an ensemble of estimators including CNN, RNN, & LSTM under an RL framework.

Github

Monte Carlo Simulation for Asian Option Pricing

Priced Asian Option using Monte Carlo Simulation, used Control Variate technique to reduce error in price, delta & sigma of the option.

Github

Bankruptcy & Credit Analysis using Machine Learning

Performed Exploratory Data Analysis, Data pre-processing, feature engineering and applied several Machine learning algorithms to classify whether a company will go bankrupt.

Github