rcosta-git

Rob’s Quant Econ and Algo Trading Resource Page

📚 Navigation 📊     [ Home | About Me ]

Hi everyone, this is Rob’s page on quantitative finance and algorithmic trading. A lot of what happens at the hedge funds doing quantitative analysis is quite secretive, but I am hoping to work on making some finance models more accessible, while keeping some of the code I develop still private between me and my collaborators. Below is some published literature on portfolio analysis and hedging, lists of research journals, classic economics texts, options and futures video tutorials, and more. Investors should contact me at Acadia Analytics LLC. A prototype of our platform is available here, and I’m actively fundraising to improve it. For math and logic, see my Google Drive. For academic questions, contact me at my Tufts email.

Table of Contents

Quantitative Financial Analysis and Trading: Start Here

Introduction

Interactive Brokers (IBKR) has a nice introduction to algorithmic trading and a well-documented API, alongside brokers like TastyTrade, E*Trade and Webull. I essentially see three types of accessible short-term quantitative trading strategies:

  1. Statistical Arbitrage: It involves identifying a statistical relationship between two or more assets and profiting from the mispricing of the assets (pairs trading).
  2. Momentum Trading: Using machine learning algorithms and indicators to identify short-term momentum and scalping profits from temporary long or short positions or options.
  3. Collecting Premiums: Identifying options with high premiums and profiting from the selling of the options. This can also involve rangebound strategies like “the wheel.”

While my focus is currently on short-term trading, I also have an interest in long-term trading and investment. Quantitative strategies could also take the form of studying a company’s balance sheet, competitive positioning, and management practices, and assigning a value to the company based on these factors, engaging in value investing. Building up portfolios of undervalued stocks and holding them for the long term could form one component of this strategy, while diversifying and rebalancing portfolios according to mean-variance analysis, or “modern portfolio theory,” as first developed by Markowitz.

Video lecture series

Here are a few lecture series on financial mathematics, probability, statistics, and machine learning:

Reference Textbooks and articles on core concepts

This is a selection of good reference articles and books, organized by publication date:

Recent Research

Here is a list of some top academic journals:

Articles on Machine Learning, Mathematical Finance, and High-Frequency Trading

Here are some recent articles I found, some of which are from researchers I met presenting on their work at the 2025 Joint Math Meetings. An older but relevant article that Tufts University president Kumar told me he wrote is Multidimensional portfolio optimization with proportional transaction costs (Muthuraman & Kumar, 2006).

Unpublished AMS abstracts

These abstracts are all from the 2025 Joint Math Meetings, but were not yet published.

Classic and Historic Economic Literature References

This list contains landmark texts in the history of economics from the last several hundred years. It is an incomplete list, and I wouldn’t say it’s necessary to read them all, but skim through anything that is of interest and be aware of the timeline:

Books on trading psychology and methodology

A lot of what makes someone a good trader is their ability to stick to their system and set emotions aside. One author has even suggested applying the 12 steps to achieve the emotional sobriety necessary for effective trading. While using an automated system may resolve some of these issues, I’d still recommend taking a look at these for the perspective:

Mathematicians who have had trading success

I find inspiration in seeing the successes of others from a math background who have applied similar techniques:

Further Video References

I haven’t watched all of these, but I’ve gone through most of them and found them helpful, for those who learn by watching:

Hidden Markov Models & Bayesian Methods

Long Short-Term Memory (LSTM) & Recurrent Neural Networks (RNN)

Automated analysis and trading in python

Understanding options

Options contracts are a type of derivative instrument, because they are derived from an underlying asset (a security specified by a stock symbol), a strike price, and an expiration date. A call option gives you the right to buy 100 shares of a security at the strike price before the expiration date, and a put option gives you the right to sell 100 shares of a security at the strike price before the expiration date. The current value of an options contract is a function of the time remaining until expiration, the current price of the underlying security, and the volatility. The intrinsic value is the amount of money that can be made by exercising the contract at expiration if it were to expire today; if it expires in the money, meaning the stock price is currently above the strike price for calls, or below the strike price for puts, then this is given by the difference between the current price of the stock and the strike price, multiplied by 100. Otherwise, it is out of the money, and the intrinsic value is just $0 (it has no intrinsic value). The extrinsic value (or time value) is the value derived from the uncertainty and volatility when there is still time remaining until expiration. The total value is the sum of these. Since the time value exponentially decays down to $0 by the expiration date (a process called “theta decay” or “time decay”), at expiration the total value of the option is just the intrinsic value, which may also be $0. Holders of options contracts often will try to sell before expiration, to avoid the decaying value. Sellers of options profit from time decay, but may still close before expiration to limit risk. Complex options strategies may have multiple legs, composed of buying and selling calls and puts at various strike prices and expiration dates, but they are still always either net long or net short on the underlying.

Understanding futures

Futures, like options, are also a type of derivative, whose price is based on an underlying asset, whether it’s an index (e.g., for E-mini S&P futures contracts), or commodities like gold, Bitcoin, corn, and oil. While futures have an expiration date, and quite a bit of leverage, their profit and loss settles to the difference with the underlying more linearly, in a way that is more comparable to forex. The margin requirements offset the leverage they provide, and further leverage can be provided by trading options on futures.

Understanding forex

Forex (foreign exchange) trading involves the global decentralized market for currency exchange. Unlike futures (which operate 23/5), the spot forex market operates 24/5, and is traded in pairs of currencies (e.g., USD/JPY, GBP/USD, etc.). Currency futures, also known as an FX future or a foreign exchange future, is a futures contract to exchange one currency for another at a specified date in the future at a price (exchange rate) that is fixed on the purchase date.

GitHub repositories

Medium articles

© 2025 Robert Costa. All rights reserved.