The 99% Market Sentiment Index

We build a market sentiment index based solely on the changes over time in the number of different stocks held by individual investors. No prices, returns or trading volumes enter the definition and trades of unwealthy and underdiversified investors are overweighted in our sentiment index. Using the trades and portfolios of a large sample of 87,373 French investors over a eight-year period, we show that our index outperforms other usual indices (based on surveys, macro-economic variables or buy-sell imbalances) in predicting short-term returns on long-short portfolios based on size or on the book-to-market ratio. An increase of one standard deviation of our market sentiment index in a given month implies a decrease of 1.05% of the return on such a long-short size based portfolio the following month. A simple dynamic strategy driven by our sentiment index delivers a Sharpe ratio higher than that of random dynamic strategies in 99.6% of cases and a much higher Sharpe ratio than the one of a buy-and-hold strategy.