Methods for trade decision making
View Patent ↗A method of trading assets on a market including: (1) receiving price data for an asset over one or more computer networks; (2) receiving current system position information; (3) storing the received asset price data and current system position information in a computer-readable medium; (4) calculating trade recommendation information form each of one or more trading sub-models, wherein each sub-model is based on a different time horizon, the calculation based on the received asset price data; and (5) calculating a trade recommendation regarding the asset based on the trade recommendation information from each of the trading sub-models. Each sub-model preferably includes: (1) a price collector component; (2) a price filter component; (3) a price database component; (4) a gearing calculator component; (5) a deal acceptor component; and (6) a book-keeper component.
1. A method of trading assets on a market, comprising the steps of:
(a) receiving price data for an asset over one or more computer networks;
(b) receiving current system position information;
(c) storing said received asset price data and said current system position information in a computer-readable medium;
(d) calculating trade recommendation information from each of a plurality of trading sub-models; wherein each sub-model is based on a different time of day, said calculation based on said received asset price data;
(e) calculating a trade recommendation regarding said asset based on said trade recommendation information from each of said trading sub-models.
2. A method as in claim 1 , wherein 24 sub-models are used.
3. A method as in claim 1 , further comprising the step of evaluating the performance of said sub-models using a risk-sensitive performance measure.
4. A method as in claim 3 , wherein said risk-sensitive performance measure is used to optimize the performance of the trading models.
5. A method as in claim 3 , wherein said risk-sensitive performance measure is an effective return.
6. A method as in claim 1 , wherein each sub-model comprises:
(a) a price collector component;
(b) a price filter component;
(c) a price database component;
(d) a gearing calculator component;
(e) a deal acceptor component; and
(f) a book-keeper component.
7. A method as in claim 1 , wherein the step of calculating a trade recommendation regarding said asset based on said trade recommendation information from each of said trading sub-models is performed by summing weighted trade recommendations of the sub-models.
8. A method as in claim 1 , wherein the step of calculating a trade recommendation regarding said asset based on said trade recommendation information from each of said trading sub-models is performed by summing weighted trade recommendations of N sub-models within the last T hours, where N and T are positive integers.
9. A method as in claim 1 , wherein the step of calculating a trade recommendation regarding said asset based on said trade recommendation information from each of said trading sub-models is based on a ratio obtained by summing weighted trade recommendations of N sub-models within the last T hours, where N and T are positive integers and dividing that sum by the total number of sub-models.
10. A method as in claim 1 , wherein each sub-model is based on a triplet comprising price change and volatility data calculated at regular intervals of a basic grid interval.
11. A method as in claim 10 , wherein the volatility is measured as a mean of absolute log price change.
12. A method as in claim 11 , wherein the mean is taken over the last M consecutive observations of log price change over the basic grid interval, where M is a positive integer.