Predict Daily Stock Prices And Automate A Day Trading Strategy [Algo Trading Projects]

3 min read


About The Presentations

This session has project presentations by two of our esteemed EPAT alumni. First on “Predict daily stock prices with random forest classifier, technical indicators and sentiment data” by Renato Votto, UK; and second on “How to automate an options day trading strategy” by Ujjwal Agrawal, India.


Project 1: Predict daily stock prices with random forest classifier, technical indicators and sentiment data

An interactive program to train a Random Forest Classifier to predict Tesla daily prices using technical indicators and sentiment scores of Twitter posts, backtesting the trading strategy and producing performance metrics.

The project leverages techniques, paradigms and data structures such as:

  • Functional and Object-Oriented Programming
  • Machine Learning
  • Sentiment Analysis
  • Concurrency and Parallel Processing
  • Direct Acyclic Graph (D.A.G.)
  • Data Pipeline
  • Idempotence

The intention behind this project was to implement the end-to-end workflow of the backtesting of an Algorithmic Trading strategy in a program with a sleek interface, and with a level of automation such that the user is able to tailor the details of the strategy and the output of the program by entering a minimal amount of data, partly even in an interactive way.

This should make the program reusable, meaning that it's easy to carry out the backtesting of the trading strategy on a different asset. Furthermore, the modularity of the software design should facilitate changes to adapt the program to different requirements (i.e. different data or ML models).

Project Code

The complete code of the project is available on Renato's Github account.

Presentation Slides


Project 2: How to automate an options day trading strategy

The aim of the project is to automate a strategy as simple as an Intraday straddle/strangle which requires complex backtesting and quantitative analysis to ascertain statistical significance and quantitative edge in trading. Index options are back-tested for straddles and strangles with varying strike differences and stop losses using Python and Excel.

The Strategy involves shorting a Straddle or Strangle at a fixed time in the morning, placing a stop loss for both legs and squaring off all or remaining positions at a fixed time before market close.

No positions will be carried over as it is an Intraday strategy that helps in avoiding any big gaps in overnight positions. This strategy can be classified as both Non-Directional and Trend Following as it performs well in either case and it struggles only when the index is extremely choppy and moves in a zig-zag way hitting both stop losses.

Presentation Slides


Presenters

Renato Votto (A Data analyst from United Kingdom)

Renato Votto pic

Renato genuinely enjoys and thrives on developing software for automation, finding algorithmic solutions for complex problems and optimising programs. He possesses a quantitative edge and is proficient in Algorithmic Trading, Quant Development, Machine Learning, Data Engineering, Python, C++, and SQL.

Renato has a background in Energy Engineering and is an alumnus of the Executive Programme in Algorithmic Trading (EPAT). Before enrolling in EPAT, he had also completed Machine Learning and Data Engineering studies.

Currently working as an analyst at the Office For Gas and Electricity Markets (OFGEM), he is mainly involved in the development of software and tools for quantitative analysis and systematic identification of market manipulation.

He is a Cryptocurrencies enthusiast, an avid rock and roll listener, loves to code, a mediocre guitar strummer, and when he is outdoors you might find him taking weird photographs.

Ujjwal Agrawal (A Quantitative Trader and A Business Owner from India)

Ujjwal Agrawal pic

Ujjwal Agrawal is a CFA (Chartered Financial Analyst) Level 3 candidate and has a bachelor’s degree in Mechanical Engineering from Pune University. He is a business owner in the Agri Processing Industry in Odisha and has been trading in the Indian Markets for the past 4 years. Managing a business and trading full time becomes difficult at times and this led him towards automating his trading setups.

Completing the EPAT course and with the help of unconditional support from the QuantInsti team, Ujjwal has now completely automated his trading setups and devotes his full time towards his businesses.

His project “Intraday Straddles” was the first setup to be fully automated among many and now he researches and combines uncorrelated setups to generate decent returns with minimum drawdowns.


This session was conducted on:
Tuesday, February 8, 2022
8:30 AM ET | 7:00 PM IST | 9:30 PM SGT