Skip to main content
Trading & Risk

What Does Not Work, and the Data

Pomegra Learn

What Does Not Work, and the Data

Technical analysis has an image problem. Search any finance forum or academic paper, and you will find fierce debate: Does it work? Is it pseudoscience? The truth is less dramatic and far more useful than either extreme. Technical analysis does not work the way many beginners believe it does—there is no holy-grail indicator, no pattern with 80% accuracy, no free edge waiting to be found. But the data also does not say technical analysis is worthless.

This chapter cuts through the noise with brutal honesty. We examine what academic research actually shows, where most backtests mislead you, why survivorship bias inflates success stories, and what retail traders can realistically expect. You will learn to distinguish between what the data supports and what traders imagine—a critical skill that most traders never develop. By the end, you will have realistic expectations about technical analysis and understand which tools and approaches stand up to scrutiny.

Why this matters​

Millions of traders lose money because they were sold a fantasy. A glossy trading course promises 75% win rate. YouTube channels cherry-pick winning trades. Backtests show fictional profits. When reality arrives—when your 75% win-rate system loses six trades in a row—the disappointment and confusion are profound.

This chapter is the antidote. Understanding what the data actually supports is not demoralizing; it is liberating. It lets you avoid the traps that destroy most new traders, set realistic expectations, and focus your effort on what actually works instead of chasing mirages.

What you will learn​

Across the articles in this chapter, you will discover:

  • How the random walk hypothesis challenges technical analysis and why the debate matters to your trading.
  • What academic research consistently finds about chart patterns, indicators, and trend-following—and where academic conclusions fall short for retail traders.
  • The deadly impact of survivorship bias: why the best traders you know about are probably survivorship bias in action.
  • How curve-fitting and overfitting ruin backtests and create systems that work perfectly on historical data but fail in real time.
  • The backtesting pitfalls that inflate returns: look-ahead bias, slippage assumptions, transaction costs, and how to spot them in your own work.
  • What the data does support: which technical approaches—trend-following, volatility measurement, support-and-resistance zones—hold up under scrutiny.
  • Realistic expectations for retail traders: how to think about edge, sample size, and long-term performance.

How to read this chapter​

Read these articles in order. They build from theory (what random walk and academic studies say) through common pitfalls (how backtests deceive) to practical insight (what the data actually supports). We assume basic familiarity with backtesting and the tools described in earlier chapters. This chapter is intentionally skeptical and data-driven; if it conflicts with promises you have heard from trading gurus, that is the point.

By the final articles, you will have a clear-eyed framework for evaluating any technical analysis claim and will know which results to trust and which to question.

Articles in this chapter​