Wisdom of crowds and commodity pricing

Abstract

We extract commodity‐level sentiment from the Twittersphere in 2009–2020. A long–short strategy based on sentiment shifts more than doubles the Sharpe ratio of extant commodity factors. Commodities with lower (higher) sentiment shifts tend to be overvalued (undervalued) when the aggregate market is in backwardation (contango). The sentiment premium is more pronounced during periods of macro contraction and deteriorating funding liquidity. While the premium concentrates in commodities with higher tweet intensity, sentiment extracted from influential tweets (i.e., high number of retweets/likes) does not exhibit stronger predictive ability than low‐attention tweets. Consistent with the overreaction hypothesis, the sentiment premium fully reverses 3 years postformation.

Commodity premia and risk management

“…We first rule out the possibility that the performance improvements in factors reaped by trailing‐stop are regime‐dependent, and it was only effective before financialization when factor performance was the strongest. In the decade leading up to Covid‐19, momentum, carry, BM, RB, and skewness experienced catastrophic drawdowns from 29% to 58% (Fan et al, 2023). Therefore, if trailing‐stop is regime‐dependent, we should observe significant reductions in Sharpe ratios in the last decade.…”

“…In the decade leading up to Covid‐19, commodity risk premia (e.g., momentum, carry, basis‐momentum [BM], relative‐basis [RB], skewness, and to a lesser extent hedging pressure [HP]) experienced catastrophic drawdowns from 29% to 58% (Fan et al, 2023). The lackluster performance of both conventional and alternative commodity risk premia strategies has resulted in a substantial decline in investor interests and fund flows into commodity trading advisor and commodity hedge funds.…”