Author(s): Shenggang Li

Originally published on Towards AI.

Harnessing Survival Analysis and Markov Decision Processes to Surpass Static ETF Performance

This member-only story is on us. Upgrade to access all of Medium.

Photo by Chris Liverani on Unsplash

Have you ever heard that 80% of hedge fund managers can’t beat the market index like SPY or QQQ? Even Warren Buffett has famously recommended that if you lack the time or expertise to pick individual stocks, you should just buy a broad index fund. This idea has become almost a mantra in the investment world.

But what if you could outperform these “one-size-fits-all” ETFs? Consider this: when you invest in an index fund, you have to buy every stock in the index — whether each one is a winner or a loser. Some stocks may perform exceptionally well, while others can drag down the overall performance. Over time, the mixture of high-performing and underperforming stocks may cancel out the growth potential that you could achieve by being more selective.

Many people intuitively understand this idea, yet only a few have applied rigorous mathematical methods or leveraged AI techniques to test and support this concept numerically.

In this paper, I present a new strategy that blends survival analysis with a Markov Decision Process (MDP) framework. First, we measure each stock’s “weakness” by calculating a hazard signal —… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI