Using Artificial Market Models to Forecast Financial Time-Series

Simple item page
dc.creatorGupta, Nachi
dc.creatorHauser, Raphael
dc.creatorJohnson, Neil F.
dc.date2005-06-15
dc.date2005-09-20
dc.date.accessioned2026-07-07T06:18:22Z
dc.date.available2026-07-07T06:18:22Z
dc.descriptionWe discuss the theoretical machinery involved in predicting financial market movements using an artificial market model which has been trained on real financial data. This approach to market prediction - in particular, forecasting financial time-series by training a third-party or 'black box' game on the financial data itself -- was discussed by Johnson et al. in cond-mat/0105303 and cond-mat/0105258 and was based on some encouraging preliminary investigations of the dollar-yen exchange rate, various individual stocks, and stock market indices. However, the initial attempts lacked a clear formal methodology. Here we present a detailed methodology, using optimization techniques to build an estimate of the strategy distribution across the multi-trader population. In contrast to earlier attempts, we are able to present a systematic method for identifying 'pockets of predictability' in real-world markets. We find that as each pocket closes up, the black-box system needs to be 'reset' - which is equivalent to saying that the current probability estimates of the strategy allocation across the multi-trader population are no longer accurate. Instead, new probability estimates need to be obtained by iterative updating, until a new 'pocket of predictability' emerges and reliable prediction can resume.
dc.description18 pages, 5 figures, added Monte Carlo algorithm tests
dc.identifierhttps://arxiv.org/abs/physics/0506134
dc.identifierhttp://arxiv.org/abs/physics/0506134
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/94712
dc.subjectPhysics and Society
dc.subjectDisordered Systems and Neural Networks
dc.titleUsing Artificial Market Models to Forecast Financial Time-Series
dc.typetext

Files

Collections

arXiv