Quantitative Finance Portfolio Projects

Given the competitive nature of finding jobs in quantitative finance, many students fall under the false pretense that having an ivy league degree, being a math olympiad, or having some outstanding technical ability is the only way to break into the industry. Suffice it to say that this notion is very far from the truth. In fact, one often underappreciated trait that quant employers look for is one's curiosity, demonstrated passion, and work ethic. It turns out that side projects are one of the best ways to highlight these attributes. Not only do candidates who have completed side projects tend to pass more resume screens, but they also tend to have more fruitful results in the interview process.

Whether you are seeking to pursue a career in quantitative trading, quantitative research, or quantitative development, working on side projects can significantly accelerate your probability of breaking into one of these fields. In this article, we'll cover a handful of tactical quantitative finance projects you can implement to create a portfolio you can later showcase to quant employers. Furthermore, we'll share what modern technologies and tools you can leverage in these projects in order to stand out from the herd.

Project #1 - Building a Trading Engine from Scratch

Quantitative Developers are responsible for building and managing a firm's trading systems. These systems take in as input market data and produce outputs which are orders. While implementing a full-functioning, robust trading system would be quite challenging, implementing a toy example would be a reasonable task. In this project, you would build a trading client that makes transaction requests and a server that receives these requests and processes them. You can find a tutorial example of this project here.

Project #2 - Machine Learning Visualization Project

Quantitative Researchers often leverage machine learning to build trading algorithms. While modern machine learning has been reduced to simple APIs like sklearn and TensorFlow, there is still a great deal of importance in understanding how these algorithms actually work. For this project, you can build a tool that visualizes a concept in machine learning. A good example of such a project is the K-Means clustering visualizer.

Project #3 - Developing a Data-Driven Investment Thesis

As a quantitative researcher, you will be exploring and developing strategies that the firm can use to make profitable financial transactions. Some of these transactions will be short-term, while others will be long-term. For this project, you can try and investigate an investment strategy by leveraging data from OpenBB. OpenBB is an investment research platform that provides free crypto, forex, futures, stocks, etc. data all from a Python API. If you are looking for some inspiration for investment strategies you can find some on this page.

Project #4 - Option Pricing Model

Options pricing models are commonly leveraged by quantitative traders and researchers to calculate the theoretical value of an option. Understanding the theoretical value of an option can allow investors to adjust their trading strategies in a way that aligns with the set of options that would reap the most profits. Since there isn't a single definitive way to calculate the theoretical value of an option, many different techniques have arisen. For this project, you can implement one of these pricing models using the programming language of your choice. Three potential pricing models include:

1/ Monte Carlo

Monte Carlo pricing relies on the statistical property known as the Law of Large Numbers. In Monte Carlo pricing, numerous random walks for the price of an underlying asset are generated, whereby each has its own associated payoff. These payoffs are averaged and discounted to today, ultimately revealing the price of the option.

2/ Binomial

The Binomial pricing model is a method for evaluating an option by using the varying price as a function of time for the financial instrument.

3/ Black Scholes

The Black Scholes is one of the most famous methods for calculating the value of an option and uses the strike price, current stock price, time to expiration, risk-free rate, and volatility to arrive at the valuation.

Project #5 - Implement a Trading Strategy and Perform Backtesting

If you're looking for a quantitative trader job, working on a project like this would be perfect. Quantitative traders are responsible for executing trades that will reap profits for the firm, so demonstrating that you've already implemented and seen success in your trading strategies will be appreciated by quant employers. Furthermore, backtesting this strategy shows that you understand a systematic process for evaluating your techniques and hypotheses. This entire project can be implemented in any programming language of your choice, but Python tends to have many libraries that will make the task slightly less arduous. Some good examples of trading strategies that you can try include:

1/ Dual Class Arbitrage

A trading strategy that involves taking advantage of the price discrepency that exists between stocks that have dual listings. (Ex: GOOG vs GOOGL)

2/ Bollinger Band Strategy

Bollinger bands are calculated by taking the 20-day simple moving average (SMA) of a stock price and then calculating the upper and lower bounds as the SMA +- two standard deviations of the actual stock price.

3/ Reinforcement Learning Algorithm

Reinforcement learning is a blossoming field in machine learning and has been leveraged in a variety of applications for algo trading. Building your own algorithm to trade a particular financial product could make for an impressive portfolio project.

4/ Sector-Based Pairs Trading Algorithm

The premise of this trading algorithm is that two assets within the same sector/industry will likely have similar performances and therefore any observed significant deviations in the prices of these assets can be capitalized on in the form of buying the falling asset or shorting the rising asset.

Conclusion

Thanks for reading this article, we hope that you found it helpful! If you're interested in finding jobs and internships in quantitative finance, check out OpenQuant, and we'll catch you next time!