Payday seasonality
SeasonalityIntermediate
The payday anomaly links stock returns to calendar dates when many households are paid. The research claim is that demand for risky assets rises around those dates. A mechanical version is a long tilt in a risky asset on the published payday window and a flat position otherwise. It is a calendar pattern tied to the civil calendar, not to price action.
Not investment advice. Nothing here is a recommendation to buy or sell anything. Backtests and historical studies are not guarantees, and a rule that worked in one sample can fail in the next. Trading can lose money. Links are for education, not endorsements. Do your own research.
- Rules
- Define the payday window in advance, typically around the turn of the month or the specific dates used in the study you are replicating. Hold the risky asset only in that window. Use the same dates every month. Do not move the window to match a rally. Trade a liquid fund, because the effect, if present, is not a stock-picking signal.
- Where AI fits
- AI can apply a fixed calendar, shift dates that fall on weekends according to a stated rule, and compare the window with the turn-of-the-month rule already on this site. If the positions are the same days, do not count them twice. Costs on a short hold have to be in the test.
- Markets
- Broad equity indexes or equity ETFs.
- Timeframes
- A few days each month.
- Risks
- Payday calendars differ by employer and country. The overlap with turn-of-the-month seasonality is large, so this can be the same effect with a new name. A short holding period dies in spreads. One decade of month-ends is still only a few hundred days.