This is to be expected, because pure time-series models (Holt-Winters, ARIMA, etc.) only capture behavior of historical data (autoregressive, i.e. yₖ = f(yₖ₋₁, yₖ₋₂, ...)). If the patterns of interest aren't primarily time-based patterns, then time series models wouldn't be predictive.
In my experience, the time-series models that are reliably predictive typically aren't purely autoregressive but contain exogeneous variables as well (i.e. yₖ = f(yₖ₋₁, yₖ₋₂, ..., xₖ, xₖ₋₁, xₖ₋₂...), like ARX models). These models don't only capture relationships to historical patterns but to other driving/causal variables.
Price forecasts are often modeled as time-series models, but this assumes that prices only have time-based patterns which is often not true. In my domains of interest for instance, time has tangible yet limited effect on prices -- prices are driven more by variables like weather and certain types of market activity.
totally agree. there is more than enough research published that confirms that simply predicting the last value is on average only marginally worse than most time series models.
In my experience, the time-series models that are reliably predictive typically aren't purely autoregressive but contain exogeneous variables as well (i.e. yₖ = f(yₖ₋₁, yₖ₋₂, ..., xₖ, xₖ₋₁, xₖ₋₂...), like ARX models). These models don't only capture relationships to historical patterns but to other driving/causal variables.
Price forecasts are often modeled as time-series models, but this assumes that prices only have time-based patterns which is often not true. In my domains of interest for instance, time has tangible yet limited effect on prices -- prices are driven more by variables like weather and certain types of market activity.