Here are my 8-thoughts and 1 solution idea about Campbell Harvey and Yan Liu recently released paper on their influential concept of the factor zoo. To sum it up, it says that there are too many data-mined factors out there and that we should be using much higher t-statistics to accept factors.
Only showing the latest backtest versions without disclosing their out-of-sample degradation
Backtesting today’s static holdings (managers, asset allocations, sub-asset-classes) into the past - filled with look-ahead bias
The first risk of investing is the Drawdown Risk - the loss from the peak. The second risk of investing is the Low Return Risk - the under-performance vs. expectations over a stretched period of time.
Many people ask me why I look at such long historical data when today is surely very different from distant past. Here is how my fascination with long-run data started and why I think insights from deep history are very useful.
Factor investing has been democratized. Having spent over 15 years as an institutional portfolio manager in factor-based strategies, I am amazed at the adoption rate of these approaches. I am now often asked by investors interested in factors for free web-tools to learn and experiment with factor-based technologies, and here are some of the best free sites that I recommend for factor investing: