Abstract
Our main objective in this paper is to revisit Markowitz’s (1952) mean-variance approach by applying Shannon Entropy as an alternative measure of financial risk. We studied 33 randomly selected stocks of the Tunis Stock Exchange, representing the daily values of the Tunindex over a period of 8 years. The obtained results indicate that entropy behaves in a similar way to standard deviation, as it decreases depending on the number of stocks held in a portfolio. Likewise, Sharpe single-index model was reinterpreted under entropy theory where total risk is divided into systematic and non-systematic risk. Then, standard measures like standard deviation or beta seem to be inadequate to assess risk and uncertainty. Consequently, entropy offers an ideal alternative to identify investment-related risk.