Electronic Trading in Order-Driven Markets: Efficient Execution

Nevmyvaka, Yuriy; Kearns, Michael; Papandreou, M.; Sycara, Katia

doi:10.1109/icect.2005.42

Cited by 7 publications

(9 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the S&L setting, orders cannot be monitored continuously and revised instantaneously, which realistically exposes them to market fluctuations and adverse selection. See (Nevmyvaka et al, 2005) for an extensive empirical study of this restricted but interesting class of strategies. Of course, we would like to be able to entertain considerably richer classes of execution strategies.…”

Section: An Rl Formulation Of Optimized Executionmentioning

confidence: 99%

“…An important example is the problem of optimized trade execution (which has also been examined in the theoretical computer science literature as the one-way trading problem). Previous work on this problem includes (Amgen and Chriss, 2002), (Bertsimas and Lo, 1998), (Coggins et al, 2003), (ElYaniv et al, 2001), (Kakade et al, 2004), and (Nevmyvaka et al, 2005). In this problem, the goal is to sell (respectively, buy) V shares of a given stock within a fixed time period (or horizon) H, in a manner that maximizes the revenue received (respectively, minimizes the capital spent).…”

Section: Introductionmentioning

confidence: 98%

See 1 more Smart Citation

Reinforcement learning for optimized trade execution

Nevmyvaka

Feng

Kearns

2006

Proceedings of the 23rd International Conference on Machine Learning - ICML '06

204

171

View full text Add to dashboard Cite

We present the first large-scale empirical application of reinforcement learning to the important problem of optimized trade execution in modern financial markets. Our experiments are based on 1.5 years of millisecond time-scale limit order data from NASDAQ, and demonstrate the promise of reinforcement learning methods to market microstructure problems. Our learning algorithm introduces and exploits a natural "low-impact" factorization of the state space.

show abstract

Section: An Rl Formulation Of Optimized Executionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 98%

Reinforcement learning for optimized trade execution

Nevmyvaka

Feng

Kearns

2006

Proceedings of the 23rd International Conference on Machine Learning - ICML '06

204

171

View full text Add to dashboard Cite

show abstract

“…This is different from the real markets where the participants would react to any event. The existing studies such as [3,8,9] have to make this assumption for backtesting strategies due to the limitation of historical order/trade data. Nevertheless, backtesting based on this assumption still makes sense because the practitioners could have a basic understanding for the new strategy and they may further improve it with penetration.…”

Section: Methodsmentioning

confidence: 99%

“…With the development of technologies such as electronic communication networks, data storage and processing, it has been feasible to optimize and backtest the new strategies on historical order/trade data. Recently, the limit order strategy for trade execution has been testified on NASDAQ data [8]. The strategy initially sets a limit order at a fixed price level till the end of execution and then submits a market order to fulfill the unexecuted volume at the end.…”

Section: Introductionmentioning

confidence: 99%

“…If some indicators forecast that prices would move toward a favorable direction, the action should not be too aggressive in order to wait for the better trading opportunities. [8,9] also discussed the above problems and proposed dynamic price adjustment in the family of limit order strategies to control nonexecution risk and respond real-time update of state variables.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Dynamic Focus Strategies for Electronic Trade Execution in Limit Order Markets

Wang

Zhang

2006

The 8th IEEE International Conference on E-Commerce Technology and the 3rd IEEE International Conference on Enterprise Computin

View full text Add to dashboard Cite

Trade execution has attracted lots of attention from academia and financial industry due to its significant impact on investment return. Recently, limit order strategies for trade execution were backtested on historical order/trade data and dynamic price adjustment was proposed to respond state variables in execution. This paper emphasizes the effect of dynamic volume adjustment on limit order strategies and proposes dynamic focus (DF) strategies, which incorporate a series of market orders of different volume into the limit order strategy and dynamically adjusts their volume by monitoring state variables such as inventory and order book imbalance in real-time. The sigmoid function is suggested as the quantitative model to represent the relationship between the state variables and the volume to be adjusted. The empirical results on historical order/trade data of the Australian Stock Exchange show that the DF strategy can outperform the limit order strategy, which does not adopt dynamic volume adjustment.

show abstract

Revisiting Agent-Based Models of Algorithmic Trading Strategies

Ponomareva¹,

Calinescu²

2014

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Algorithmic trading (AT) strategies aim at executing large orders discretely, in order to minimize the order's impact, whilst also hiding the traders' intentions. Most AT evaluation methods range from running the AT strategies against historical data (backtesting) to evaluating them on simulated markets. The contribution of the work presented in this paper is twofold. First we investigated different types of agentbased market simulations and suggested how to identify the most suitable market simulation type, based on the specific market model to be investigated. Then we proposed an extended model of the Bayesian execution strategy. We implemented and assessed this model using our tool Al-TraSimBa (ALgorithmic TRAding SIMulation BAcktesting) against the standard Bayesian execution strategy and naïve execution strategies, for momentum, random and noise markets, as well as against historical data. On the basis of the results presented in the paper, we propose that momentum market is the most suitable model for testing algorithmic trading strategies, since it quickly fills the Limit Order book and produces results comparable to those of a liquid stock. Our experiments and analysis also revealed that: (i) the method of estimating priors proposed in this paper − within the Bayesian adaptive agent model − can be advantageous in relatively stable markets, when trading patterns in consecutive days are strongly correlated, and (ii) there exists a trade-off between the frequency of decision making and more complex decision criteria, on one side, and the negative outcome of lost trading on the agents' side due to them not participating actively in the market for some of the execution steps.

show abstract

Electronic Trading in Order-Driven Markets: Efficient Execution

Cited by 7 publications

References 6 publications

Reinforcement learning for optimized trade execution

Reinforcement learning for optimized trade execution

Dynamic Focus Strategies for Electronic Trade Execution in Limit Order Markets

Revisiting Agent-Based Models of Algorithmic Trading Strategies

Contact Info

Product

Resources

About