Time Bankroll And Kalman Filters
In a number of prior posts, we have referred to the differences between mean and median outcomes of a series of trades (bets) in sports events to varying degrees.
- Time-Value Vs Expected-Value Or Likely Poverty Vs Average Riches - John Allen Paulos,
- Volatility Drag - Aaron Brown, and
- Ensemble Averages Vs Time Averages - Ole Peters.
On this occasion, we would like to explore the idea of a Time Bankroll.
Time Bankroll: Bankroll metric that reflects trader's unique time-printed sequence of trades - generated using a Kalman Filter.
Expected value summarizes the average performance across all traders and is of critical importance to the bookmaker whereas time value best reflects the most likely, individual outcome and is of paramount importance to the trader!
We can use a Kalman Filter to track our bankroll through a sequence of trades thereby mapping our unique journey through time in a single number.
First, starting with a low bankroll (1700) and ending with a somewhat higher final bankroll (2300) gives us a time bankroll (2122) which reflects that particular journey.
Second, starting with a high bankroll (2900) and ending with a somewhat lower final bankroll (2300) gives us a time bankroll (2500) which reflects a different time-print.
Note that the specific bankroll values are randomly generated and are not meant to accurately reflect relative changes from trade to trade.
In sum, given that the time bankroll better reflects our individual time-printed journey through a sequence of trades, should it form the basis for calculating future stakes?
Enjoy!