What Can Analysts Learn from Artificial Intelligence about Fundamental Analysis?

Oliver Binz from INSEAD joined us on 24 February to discuss his paper 'What can Analysts Learn from Artificial Intelligence about Fundamental Analysis?'


Presentation overview:

The authors build a machine learning algorithm grounded in fundamental analysis theory, evaluate its performance, and derive implications for equity analysts. The algorithm forecasts profitability, estimates intrinsic values, and forms portfolios based on the resulting valuations.

Findings reveal substantial out-of-sample risk-adjusted returns. Investment performance improves with the degree of disaggregation of profitability drivers and with the operating performance forecast horizon.

Perhaps surprisingly, incorporating lagged historical fundamentals or focusing only on core operating items does not enhance performance. However, allowing for non-linearities generally improves performance, the effects being strongest for small, loss-making, technology, and financially distressed firms.


Oliver Binz:

Oliver is an Assistant Professor of Accounting and Control at INSEAD. He received his PhD in Business Administration from Duke University. Prior to academia, he worked for Deutsche Bank’s Asset and Wealth Management division.

Oliver’s research interests lie at the intersection of equity valuation and macroeconomics. Some of his recent projects explore how macroeconomic developments affect managers’ and consumers’ decision making, and the resulting consequences for firms’ profits.

Oliver teaches Financial Accounting in the MBA programme.


Watch the recording and download the slides and paper below: