search

Taketrung / betting-ai

Automatically exported from code.google.com/p/betting-ai
1 stars 1 forks source link

Trader optimisation for price variable adopting neural networks #64

Closed GoogleCodeExporter closed 9 years ago

GoogleCodeExporter commented 9 years ago 
As a trader 
I want to run trader optimisation
So that I can find optimal trading strategy

Original issue reported on code.google.com by daniel.k...@gmail.com on 2 Dec 2010 at 4:54

GoogleCodeExporter commented 9 years ago 
One market with one runner is analysed.

Trader(price) = if(priceToLay)>price then placeBackBet
Quality(trader) = expected profit per each bet

10 iterations are performed.

Original comment by daniel.k...@gmail.com on 2 Dec 2010 at 4:56

GoogleCodeExporter commented 9 years ago

Original comment by daniel.k...@gmail.com on 5 Dec 2010 at 11:36

GoogleCodeExporter commented 9 years ago

Original comment by daniel.k...@gmail.com on 16 Feb 2011 at 7:55

GoogleCodeExporter commented 9 years ago

Original comment by daniel.k...@gmail.com on 4 Mar 2011 at 5:38

GoogleCodeExporter commented 9 years ago

Original comment by daniel.k...@gmail.com on 27 Mar 2011 at 12:27

GoogleCodeExporter commented 9 years ago 
- Neural network design 1
    - Input neurons, time to market time, traded volume, price, risk, etc.
    - Output neurons - each neuron represents one possible move, e.g. do nothing, place back bet, place lay bet, 

- Neural network design 2
    - Input neurons represent decision to be taken, e.g. place bet or do nothing and market situation before or after bet is placed (market price, volume, risk, etc).
    - Output neurons - a single neuron, which says how good this decision is.

- Neural network design 3
    - Input neurons represent market position after taking a given decision, e.g. market price/volume, risk, etc. This decision must be derived from delta between market positions before and after taking some action. 
    - Output neurons - a single neuron, which says how good this decision is.

Original comment by daniel.k...@gmail.com on 27 Mar 2011 at 1:05

GoogleCodeExporter commented 9 years ago 
Design predictive neural network:
- input neurons - time slices,
- output neurons - future time slices,

e.g. data set: 1 2 3 4 5 6 7

input 1,2,3 output 4
input 2,3,4 output 5

Original comment by daniel.k...@gmail.com on 27 Mar 2011 at 5:52

GoogleCodeExporter commented 9 years ago

Original comment by daniel.k...@gmail.com on 14 Apr 2011 at 7:53

GoogleCodeExporter commented 9 years ago

Original comment by daniel.k...@gmail.com on 14 Apr 2011 at 11:25

GoogleCodeExporter commented 9 years ago

Original comment by daniel.k...@gmail.com on 10 May 2011 at 12:04