Can AI predict stock prices with 90% accuracy ?

The ability of AI to predict stock prices has been a topic of discussion in recent years. With the rise of machine learning and big data, many experts believe that AI can be used to make accurate predictions about stock prices. However, others argue that the stock market is inherently unpredictable and that AI is not yet advanced enough to make accurate predictions. Recent studies have shown that AI can be used to analyze large amounts of data and make predictions about stock prices. But can AI really predict stock prices with 90% accuracy? This is a question that has sparked a lot of debate in the financial community. The potential consequences of AI being able to predict stock prices with high accuracy are significant, and could potentially change the way that investors make decisions. As AI technology continues to evolve, it will be interesting to see if it can live up to its promise in this area.

AI cannot currently predict stock prices with 90% accuracy. While machine learning models, including deep learning and transformers, can process vast amounts of market data to identify patterns or trends, financial markets are inherently noisy, non-stationary, and influenced by unpredictable external factors such as geopolitical events or black swan occurrences. State-of-the-art research reports best-case accuracies for directional movement predictions (e.g., up vs. down) in the range of 50–60%, far below the 90% threshold, and even those models typically fail to generalize across different market regimes. High-frequency trading firms with proprietary models and extensive data resources still face significant uncertainty, underscoring the fundamental difficulty of achieving such precision.

— Enriched May 12, 2026 · Source: best-effort summary, no public reference