Strategies · Library · Stocks
§3.9.1Mean reversion
Mean-reversion – multiple clusters
A variant of §3.9 Mean-reversion – single cluster
Repeat the single-group fade across several groups, such as sectors, each demeaned against its own average. A regression on group membership gives the same answer in one step, and groups can be funded evenly.
Open in the builderAs a long-only proxy; see how ARCANE uses it.
- Asset class
- Stocks
- Held for
- Days
- Data
- ARCANE has part of the data
- Symphony
- Builds as a long-only proxy
The rule
- Signal
- Each stock's return minus its own group's average return.
- Entry and exit
- Rebalance often; each group's bets close as gaps close.
- Sizing
- Per-group proportional positions, groups funded equally, whole book dollar-neutral.
How it fails
- Group definitions drive results
- Short leg needed
- High turnover
- Sector-wide moves can persist
Data it needs
- daily prices
Prices exist, but ARCANE has no sector classification table for stocks beyond the sector ETFs.
How ARCANE uses it
A Call comparing a company to its sector can use this framing if a group list is supplied.
Builds as a long-only proxy. Use sector ETFs as clusters and hold each cluster's laggard; the many-stock universe and shorts are lost.
Filed under the mean reversion card
Buy last week’s biggest losers and sell last week’s biggest winners, betting that short, sharp moves partly undo themselves.
A paper plan from this card holds 1 to 10 days, stops at 1× the expected move and uses at most 50% of your risk budget. The card
Source: Kakushadze and Serur (2018), 151 Trading Strategies, §3.9.1, p. 48 of the SSRN version. Described in our words. Mean reversion is ARCANE’s filing, not the book’s.