You’re in for a special treat.

Today’s newsletter is taken directly from my best-selling course for quant finance, Getting Started With Python for Quant Finance.

I dive deep into edge in the course and today you’ll get a preview.

Edge starts with market inefficiencies which are predictable, recurring asset mispricings.

Identifying these patterns and trading them is where edge comes in.

And edge is what keeps algorithmic traders trading.

Let’s dive in.

Finding your trading edge: Exploit asset mispricing (over and over)

What Are Market Inefficiencies?

Market inefficiencies are temporary asset mispricings caused by trader psychology, economic shifts, market microstructure quirks, or specific company events.

These inefficiencies aren’t random—they repeat and can be exploited if detected early and accurately.

Every inefficiency represents an opportunity to buy “cheap” and sell “expensive.”

Our goal is to detect, predict, and act on these patterns before the broader market corrects them.

Understanding Edge

You have an edge when you have positive expected value from exploiting a market inefficiency.

It’s not about winning every trade. It’s about creating a system where the long-term probability-weighted payoff is positive.

What if proposed a game.

Roll a six-sided die. If it lands on 5 or 6, you win $1,000, otherwise, you get nothing.

The question is how much would you pay to play this game?

To answer, you need to know the expected value of the game.

With two winning outcomes out of six, the expected value of a single roll is (2 / 6) × 1000 = $333.34.

If you were offered a chance to pay anything less than $333.34 to play the game, you should as many times as possible. An infinite number of times, actually, since you expect to make $333.34 over the long run.

If you can pay less than $333.34 to pay, you have an edge.

It works the same way in trading.

Investing Factors: Models of Market Inefficiency

An investment factor is a model of a market inefficiency. It is the tool that lets you to formalize and trade on your edge.

Factors fall into three broad categories:

1. Technical Factors: Derived from price patterns, volume, and other technical indicators.
2. Fundamental Factors: Based on financial statement data like earnings, book value, or growth metrics.
3. Statistical Factors: Built on latent patterns identified through statistical or machine learning techniques.

Modern quants often combine these factors into advanced multi-factor models. By doing so, they can isolate and amplify their edge while diversifying away unwanted risks.

I spend a full 270 minutes discussing how to build, backtest, and trade factors in Getting Started With Python for Quant Finance.

Alpha: The Ultimate Result

Alpha is the culmination of all this hard work.

Alpha are superior returns achieved relative to a benchmark. Your alpha is a byproduct of your ability to detect inefficiencies, model them through factors, and exploit them systematically.

But here’s the harsh truth: alpha isn’t guaranteed. The market is constantly evolving, and inefficiencies that generate today’s alpha might vanish tomorrow. This is what we call alpha decay.

That’s why continuous iteration—testing, refining, and adjusting—is critical for maintaining your edge.

Putting It All Together

To summarize:

• Market inefficiencies are opportunities that arise from predictable mispricings.
• Edge is the mechanism to exploit those inefficiencies with positive expected value.
• Investing factors model inefficiencies for systematic trading.
• Alpha is the superior return generated when everything aligns.

As quant traders, our task is to build systems that find and exploit inefficiencies consistently. It’s not about perfection but about achieving sustainable success over the long term.