Prediction-Based Limit Order Trading by Christopher Felder :: SSRN - Fotograf Malin Grönborg

Prediction-Based Limit Order Trading by Christopher Felder :: SSRN


The larger the inventory is, be it positive or negative , the higher the holder’s exposure to market movements. Hence, market makers try to minimize risk by keeping their inventory as close to zero as possible. Market makers tend to do better in mean-reverting environments, whereas market momentum, in either direction, hurts their performance.

  • The successive orders generated by this procedure maximize the expected exponential utility of the trader’s profit and loss (P&L) profile at a future time, T , for a given level of agent inventory risk aversion.
  • For each subsequent generation 45 new individuals run through the data and then added to the cumulative population, retaining all the individuals from previous generations.
  • Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.

The selection of features based on these three metrics reduced their number from 112 to 22 . The target for the random forest classifier is simply the sign of the difference in mid-prices at the start and the end of each 5-second timestep. That is, classification is based on whether the mid-price went up or down in each timestep. Balancing exploration and exploitation advantageously is a central challenge in RL. The Q-value iteration algorithm assumes that both the transition probability matrix and DOGE the reward matrix are known.

Journal of Financial Markets

This snapshot data provides us with the opportunity to leverage the longer tick-time interval and make profits using machine learning algorithms. Genetic algorithms compare the performance of a population of copies of a model, each with random variations, called mutations, in the values of the genes present in its chromosomes. This process of random mutation, crossover, and selection of the fittest is iterated over a number of generations, with the genetic pool gradually evolving.


But when volatility rises and client flows become one-sided, market-makers must quickly pivot to external venues to hedge their risks. Whether to skew prices and wait for offsetting client flow, or hedge with other dealers in the open BNB market, is a decision that is usually left to traders. But traders have little more than their judgment and experience to go by.

A comprehensive guide to Avellaneda & Stoikov’s market-making strategy

In Section 2, we introduce some basic concepts and describe the input LOB datasets. For a single tick, the computation time required for the main procedures is recorded in Table 8. In addition to the algorithmic calculations, we reserve time for some mechanical order-related activities, such as order submission and execution in exchanges.

  • Other indicators, such as the Sortino ratio, can also be used in the reward function itself.
  • It’s easy to see how the calculated reservation price is different from the market mid-price .
  • With these values, the AS model will determine the next reservation price and spread to use for the following orders.
  • Consequently, the Alpha-AS agent adapts its bid and ask order prices dynamically, reacting closely (at 5-second steps) to the changing market.

This parameter, denoted by the letter gamma, is related to the aggressiveness when setting the spreads to achieve the inventory target. It is directly proportional to the asymmetry between the bid and ask spread. It sets a target of base asset balance in relation to a total asset allocation value .

Reinforcement Learning Approaches to Optimal Market Making

Wireless ad hoc networks are infrastructureless networks and are used in various applications such as habitat monitoring, military surveillance, and disaster relief. Data transmission is achieved through radio packet transfer, thus it is prone to various attacks such as eavesdropping, spoofing, and etc. Monitoring the communication links by secure points is an essential precaution against these attacks. Also, deploying monitors provides a virtual backbone for multi-hop data transmission.

The Chinese A-share market can satisfy this tick-time condition with its update frequency of 3 s. Our empirical study shows that our deep LOB trading system is effective in the context of the Chinese market, which will encourage its use by other traders. Mann-Whitney tests comparing the four daily performance indicator values (Sharpe, Sortino, Max DD and P&L-to-MAP) obtained for the Gen-AS model with the corresponding values obtained for the other models, over the 30 test days. Number of days either Alpha-AS-1 or Alpha-AS-2 scored best out of all tested models, for each of the four performance indicators.

A reinforcement learning approach to improve the performance of the Avellaneda-Stoikov market-making algorithm

So, if we’re ing more or less the same things, all good/accurate models tend to be analogous; they must correspond to one another if they each correspond to the same underlying physical phenomena. Stay informed on the latest trending ML papers with code, research developments, libraries, methods, and datasets. Comparison of values for Max DD and P&L-to-MAP between the Gen-AS model and the Alpha-AS models (αAS1 and αAS2). If you want to end the trading session with your entire inventory allocated to USDT, you set this value to 0. Starting with the strategy name, you have to enter avellaneda_market_making to use this new strategy.

An early stopping strategy is followed on 25% of the training sets to avoid overfitting. The architecture of the target DQN is identical to that of the prediction DQN, the parameters of the former being copied from the latter every 8 hours. Mean decrease accuracy , a feature-specific estimate of average decrease in classification accuracy, across the tree ensemble, when the values of the feature are permuted between the samples of a test input set .

This kind of scales generate ordinal variables made up of a set of rank ordered items. Since the distance between two consecutive items cannot be either defined or presumed equal, this kind of variable cannot be analysed by either statistical methods defined on a metric space or parametric tests. Therefore, Likert-type variables cannot be used as segmentation variables of a traditional cluster analysis unless pre-transformed. In such context, fuzzy numbers have been suggested as a way to recode Likert-type variables. Fuzzy numbers are defined by a membership function whose form is usually determined by an expert.

This half a second enables our system, which is trained with a deep-learning architecture, to integrate price prediction, trading signal generation, and optimization for capital allocation on trading signals altogether. It also leaves sufficient time to submit and execute orders before the next tick-report. Besides, we find that the number of signals generated from the system can be used to rank stocks for the preference of LOB trading. We test the system with simulation experiments and real data from the Chinese A-share market. The simulation demonstrates the characteristics of the trading system in different market sentiments, while the empirical study with real data confirms significant profits after factoring in transaction costs and risk requirements. Optimisation problems such as this one can be difficult to solve using model-free deep learning approaches due to the large number of variables, which necessitate a huge amount of training data.

Conversely, test avellaneda-stoikov for which the Alpha-ASs did worse than Gen-AS on P&L-to-MAP in spite of performing better on Max DD are highlighted in red (Alpha-AS “worse”). On the P&L-to-MAP ratio, Alpha-AS-1 was the best-performing model for 11 test days, with Alpha-AS-2 coming second on 9 of them, whereas Alpha-AS-2 was the best-performing model on P&L-to-MAP for 16 of the test days, with Alpha-AS-1 coming second on 14 of these. Here the single best-performing model was Alpha-AS-2, winning for 16 days and coming second on 10 (on 9 of which losing to Alpha-AS-1). Alpha-AS-1 had 11 victories and placed second 16 times (losing to Alpha-AS-2 on 14 of these).

Market-making by a foreign exchange dealer –

Market-making by a foreign exchange dealer.

Posted: Wed, 10 Aug 2022 07:00:00 GMT [source]

Again, the of selecting a specific individual for parenthood is proportional to the Sharpe ratio it has achieved. A weighted average of the values of the two parents’ genes is then computed. Therefore, by choosing a Skew value the Alpha-AS agent can shift the output price upwards or downwards by up to 10%. Market indicators, consisting of features describing the state of the environment. We model the market-agent interplay as a Markov Decision Process with initially unknown state transition probabilities and rewards. The reservation price is highly influenced by the election of the parameter T isn’t it?

deep lob trading

No Comments

Sorry, the comment form is closed at this time.