Portfolio

About Me

(Work in Progress)

For more information, please scroll through the page — my CV and academic recommendation letters are available at the bottom.

Technical Skills

Please refer to ‘On-going certifications’ section for technical skills I am currently learning/developing.
Note that conceptual/modelling list is not exhaustive as it does not include financial models.

Languages / Software

Python, STATA, EViews, LaTeX, CLI, Git, GitHub, Kpler, Refinitiv Eikon, S&P Global (Platts, Capital IQ), Power BI, Power Automate, Excel, Google Cloud (Basic), Sierra Chart, MetaTrader5

Libraries / Frameworks

pandas, NumPy, matplotlib, seaborn, scipy, statsmodels, scikit-learn, streamlit, plotly

Conceptual / Modelling

Data Pre-processing, EDA, Feature Engineering, Probability Distributions (Normal, Binomial, Poisson – PMF/PDF/CDF), Statistical Validation (t-tests 1- & 2-sided, chi-square, ANOVA, Tukey HSD, binomial tests), Time Series Modeling (ARIMA, VAR, VECM, GARCH), Econometric Causality (Cointegration, Granger causality, Impulse Response, FEVD), Machine Learning (Regression (Linear, Logistic), K-Nearest Neighbors (Classifier, Regressor))

Publications (Working Papers)

(Work in Progress)

Completed Projects

Click the project title to visit the interactive dashboard

Options Strategy Payoff Calculator

Developed a robust web application that allows users to analyze a wide range of options trading strategies, including Long Call, Short Call, Long Put, Short Put, Bull Call Spread, Bear Put Spread, and more.
Empowers users to easily input key parameters such as strike price, premium, and expiration prices. The application generates detailed net-payoff tables and dynamic graphs, aiding seasoned analysts and students alike in making informed decisions.
Utilised popular libraries such as numpy, pandas, matplotlib, and streamlit to create a user-friendly interface. This enhances strategy interpretation, providing valuable insights into payoffs and break-even points for various options strategies.

Options Pricing and Greeks Analysis

Developed an options pricing tool using Black-Scholes and Monte Carlo methods, comparing options price sensitivity to volatility, time to expiration, and strike price, with visualisations of Monte Carlo price paths and distributions.
Implemented Greek analysis for both methods, and created multi-dimensional sensitivity plots for deeper insights into option pricing dynamics.

Pairs Trading Simulator

Built a rudimentary pairs trading sim for an aluminium and lead asset pair with customisable parameters like z-score threshold, lookback period, lot sizes, stop loss, and take profit, enabling flexible strategy testing.

A VAR Analysis of the Nominal Broad US Dollar Index (NBUSDI), Dow Jones Industrial Average (DJI), and S&P 500 (SPX)

Explored the impact of changes in the NBUSDI, DJI, and SPX on each other, aiming to understand the short-term interactions and causal dynamics among these key financial indicators.
Identified robust autocorrelation in NBUSDI, suggesting enduring shocks influencing the index, while DJI and SPX exhibited limited immediate influence on NBUSDI, emphasising their relative independence.
Granger causality tests revealed significant evidence that lagged variables collectively Granger-cause changes in NBUSDI, highlighting the importance of external factors and predictive relationships among financial variables.

Assessing the impact of oil rents on UAE GDP: A multivariate time series regression analysis

A study exploring the impact of oil rents on the economic growth of the United Arab Emirates (UAE), focusing on the effectiveness of existing strategies.
Addressed the model’s limitations, including non-stationarity and multicollinearity, and proposed solutions such as the inclusion of new variables like merchandise imports to enhance model robustness and reliability.
Found that oil rents significantly influence the UAE’s economic growth, with a notable contribution to GDP despite government strategies aimed at diversification.

On-going Certifications

Note that I am not pursuing all of these certifications at once.
I have a systematic learning plan where I attempt to complete short ‘courses’ frequently whilst making progress towards skill/career path certifications and balancing my research commitments.

Career Path (50-150 hours -> with exams)

Machine Learning / AI Engineer
Data Scientist: Machine Learning Specialist
Data Scientist: NLP Specialist
Data Scientist: Inference Specialist
Data Scientist: Analytics
Data Engineer
Fullstack Engineer

Skill Path (>20 hours)

Analyze Data with SQL
Analyze Data with R
Feature Engineering
Build a Machine Learning Model
Intermediate Machine Learning
Build Deep Learning Models with TensorFlow

Courses (1-20 hours)

Learn SQL
Learn MongoDB
kdb+/q Developer – Level 1
kdb+/q Developer – Level 2
kdb+/q Developer – Level 3
Learn R
Generative AI Models: Generating Data Using Generative Adversarial Networks (GANs)
Intro to PyTorch and Neural Networks
Creating AI Applications using Retrieval-Augmented Generation (RAG)
Generative AI Models: Getting Started with Autoencoders
Generative AI Models: Generating Data Using Variational Autoencoders
Learn Image Classification with PyTorch

Algorithm Trading Courses (1-20 hours)

Introduction to Machine Learning for Trading
Trading with Machine Learning: Classification and SVM
Options Trading Strategies in Python: Advanced
Trading with Machine Learning: Regression
Python for Machine Learning in Finance
Mean Reversion Strategies in Python
Backtesting Trading Strategies
Event Driven Trading Strategies
Financial Time Series Analysis for Trading
Futures: Concepts & Strategies
Systematic Options Trading
Options Volatility Trading: Concepts and Strategies
Data and Feature Engineering for Trading
Decision Trees in Trading
Natural Language Processing in Trading
Unsupervised Learning in Trading
Neural Networks in Trading
Deep Reinforcement Learning in Trading
Machine Learning for Options Trading
Quantitative Portfolio Management
Position sizing in Trading
Factor Investing: Concepts and Strategies
Portfolio Management using Machine Learning: Hierarchal Risk Parity
AI for Portfolio Management: LSTM Networks
News Sentiment Trading Strategies
Momentum Trading Strategies
Trading Alphas: Mining, Optimisation, and System Design
Trading in Milliseconds: MFT Strategies and Setup

Saimanish Prabhakar

Portfolio

About Me

Technical Skills

Languages / Software

Libraries / Frameworks

Conceptual / Modelling

Publications (Working Papers)

Completed Projects

On-going Certifications

Career Path (50-150 hours -> with exams)

Skill Path (>20 hours)

Courses (1-20 hours)

Algorithm Trading Courses (1-20 hours)

Completed Certifications

Skill Path (>20 hours)

Courses (1-20 hours)

Algorithm Trading Courses (1-20 hours)

Finance/Industry Experience Courses (1-10 hours)

CV

Academic Recommendation Letters