search.noResults

search.searching

dataCollection.invalidEmail
note.createNoteMessage

search.noResults

search.searching

orderForm.title

orderForm.productCode
orderForm.description
orderForm.quantity
orderForm.itemPrice
orderForm.price
orderForm.totalPrice
orderForm.deliveryDetails.billingAddress
orderForm.deliveryDetails.deliveryAddress
orderForm.noItems
TRADE EXECUTION FX


The Limits of Data-driven Approaches


Market participants increasingly


acknowledge that there are a number of limitations


inherent in data-


driven methods. Machine learning or statistical a p p ro a c he s tend to be most successful where data


sets are


large. In certain markets data are


sparse, but


even in data- rich markets, those data only provide a rear- view mirror into market conditions. Any analysis based on


historical


data alone will be unable to react to changes in


market


c ond i t ion s , or structural changes in the dynamics of price formation.


condition: liquidity-squeezes, or flash crashes – for example – the behaviours of algos in these types of market will be uncertain.


Similarly, when testing execution algos, replay servers (or even


Natural Science Origins


These challenges are new in best execution but not in other


Climatologists and Particle Physicists have


scenarios


disciplines. Ecologists, been building


robust, adaptive simulators for studying what- if


for decades. The complex a d a p t i v e systems


sci e n t i s t s study


those are


modelled with a technique called a g e n t - b a s e d s i mu l a t i on . These powerful s i m u l a t ion models are able to generate streams


of


Ecologists, Climatologists and Particle Physicists have been building robust, adaptive simulators for studying what-if scenarios for decades


Tese problems are exacerbated in a world in which execution is increasingly being undertaken by algos. By design, these algos can only learn from historical data they have been fed. Where this a shortage of data around certain types of market


simulators driven by stochastic models) are unable to capture the market impact of a trade placed. Tis is because the data is not adaptive so it cannot play-out alternative scenarios. Undertaking so called “what-if” analysis has become the holy grail of execution testing.


r ea l i s ti c synthetic data for undertaking “ w h a t - i f ” analysis.


Had you tried


to build one of these high-fidelity market simulations even five years ago, you would have run into some non-trivial challenges. To run these models at the scale required to produce streams of realistic market data would have required a veritable army of sophisticated


FX TRADER MAGAZINE April - June 2019 39


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44  |  Page 45  |  Page 46  |  Page 47  |  Page 48  |  Page 49  |  Page 50  |  Page 51  |  Page 52  |  Page 53  |  Page 54  |  Page 55  |  Page 56  |  Page 57  |  Page 58  |  Page 59  |  Page 60  |  Page 61