Despite their high risk, cryptocurrencies have gained popularity as viable trading options. Cryptocurrencies are digital assets that experience significant fluctuations in a market operating 24 h a ...day. Recently, considerable attention has been paid to developing trading bots using machine-learning-based artificial intelligence. Previous studies have employed machine learning techniques to predict financial market trends or make trading decisions, primarily using numerical data extracted from candlesticks. However, these data often overlook the temporal and spatial information of candlesticks, leading to a limited understanding of their significance. In this study, we utilize multi-resolution candlestick images containing temporal and spatial information. Our rationale for using visual information from candlestick charts is to replicate the decision-making processes of human trading experts. To achieve this, we employ deep reinforcement learning algorithms to generate trading signals based on a state vector that includes embedded candlestick-chart images. The trading signal is generated using a multi-agent weighted voting ensemble approach. We test the proposed approach on two BTC/USDT datasets under both bullish and bearish market scenarios. Additionally, we use an attention-based technique to identify significant areas in the candlestick images targeted by the proposed approach. Our findings demonstrate that models using candlestick images 'as-is', outperform those using raw numeric data and other baseline models.
Although machine learning approaches have been widely used in the field of finance, to very successful degrees, these approaches remain bespoke to specific investigations and opaque in terms of ...explainability, comparability, and reproducibility.
The primary objective of this research was to shed light upon this field by providing a generic methodology that was investigation-agnostic and interpretable to a financial markets’ practitioner, thus enhancing their efficiency, reducing barriers to entry, and increasing the reproducibility of experiments. The proposed methodology is showcased on two automated trading platform components. Namely, price levels, a well-known trading pattern, and a novel 2-step feature extraction method.
This proposed a generic methodology, useable across markets, the methodology relies on hypothesis testing, which is widely applied in other social and scientific disciplines to effectively evaluate the concrete results beyond simple classification accuracy. The first hypothesis was formulated to evaluate whether the selected trading pattern is suitable for use in the machine learning setting. The second hypothesis allows us to systematically assess whether the proposed feature extraction method leads to any statistically significant improvement in the automated trading platform performance.
Experiments were conducted across, 10 contracts, 3 feature spaces, and 3 rebound configurations (for feature extraction), resulting in 90 experiments. Across the experiments we found that the use of the considered trading pattern in the machine learning setting is only partially supported by statistics, resulting in insignificant effect sizes (Rebound 7 - 0.64±1.02, Rebound 11 0.38±0.98, and rebound 15 - 1.05±1.16), but allowed the rejection of the null hypothesis based on the outcome of the statistical test. While the results of the proposed 2-step feature extraction looked promising at first sight, statistics did not support this, this demonstrated the usefulness of the proposed methodology. Additionally, we obtained SHAP values for the considered models, providing insights for adjustments to the feature space.
We showcased the generic methodology on a US futures market instrument and provided evidence that with this methodology we could easily obtain informative metrics beyond the more traditional performance and profitability metrics. The interpretability of these results allows the practitioner to construct more effective automated trading pipelines by analysing their strategies using an intuitive and statistically sound methodology. This work is one of the first in applying this rigorous statistically-backed approach to the field of financial markets and we hope this may be a springboard for more research. A full reproducibility package is shared.
•Statistically-backed method for uniform and comparable trading pattern evaluation.•Recognition and classification of price levels trading pattern in financial markets.•Use of price levels trading pattern as a part of an automated trading platform.•Domain knowledge-based feature space design.
In this paper, the application of the intuitionistic fuzzy rule-base evidential reasoning (IFRBER) to the development of a new optimized automated trading system (ATS) for the Forex market is ...presented. The used IFRBER approach represents the intuitionistic fuzzy sets in the framework of the evidence theory that allows us to avoid the revealed drawbacks of the IFS operational laws and enhance the overall performance of the IFRBER approach. It is shown that the IFRBER approach extracts from an analyzed system considerably more of useful for the decision making information than the usual fuzzy rule-base evidential reasoning (FRBER). Then based on the IFRBER, a new approach to make the justified transaction buying and selling decisions was proposed. This approach was used to develop a new optimized ATS for the Forex market. It is shown that due to the ability of a new approach to use more of useful information that present implicitly in the problem formulation than the proposed earlier usual fuzzy rule-base evidential reasoning method, the developed ATS provides a considerably more profitable and comfortable (with a higher percent of winning trades and with low risks) trading than the earlier developed ATS.
•Intuitionistic fuzzy rule-base evidential reasoning for generating trading decisions.•Automated trading system for the currency exchange (Forex) market.•Two-loops approach to the trading system optimization.•Fuzzy technical analysis indicators and their optimization.•Multiple criteria fuzzy optimization of the entire trading system.
Abstract
I introduce parameterised response zero intelligence (PRZI), a new form of zero intelligence (ZI) trader intended for use in simulation studies of the dynamics of continuous double auction ...markets. Like Gode and Sunder’s classic ZIC trader, PRZI generates quote prices from a random distribution over some specified domain of discretely valued allowable quote prices. Unlike ZIC, which uses a uniform distribution to generate prices, the probability distribution in a PRZI trader is parameterised in such a way that its probability mass function (PMF) is determined by a real-valued control variable
s
in the range
$$-1.0, +1.0$$
-
1.0
,
+
1.0
that determines the
strategy
for that trader. When
$$s=0$$
s
=
0
, a PRZI trader behaves identically to the ZIC strategy, with a uniform PMF; but when
$$s \approx \pm 1$$
s
≈
±
1
the PRZI trader’s PMF becomes maximally skewed to one extreme or the other of the price range, thereby making it more or less “urgent” in the prices that it generates, biasing the quote price distribution towards or away from the trader’s limit price. To explore the co-evolutionary dynamics of populations of PRZI traders that dynamically adapt their strategies, I show initial results from long-term market experiments in which each trader uses a simple stochastic hill-climber algorithm to repeatedly evaluate alternative
s
-values and choose the most profitable at any given time. In these experiments the profitability of any particular
s
-value may be non-stationary because the profitability of one trader’s strategy at any one time can depend on the mix of strategies being played by the other traders at that time, which are each themselves continuously adapting. Results from these market experiments demonstrate that the population of traders’ strategies can exhibit rich dynamics, with periods of stability lasting over hundreds of thousands of trader interactions interspersed by occasional periods of change. Python source code for PRZI traders, and for the stochastic hill-climber, have been made publicly available on GitHub.
Abstract
We study discrete‐time predictable forward processes when trading times do not coincide with performance evaluation times in a binomial tree model for the financial market. The key step in ...the construction of these processes is to solve a linear functional equation of higher order associated with the inverse problem driving the evolution of the predictable forward process. We provide sufficient conditions for the existence and uniqueness and an explicit construction of the predictable forward process under these conditions. Furthermore, we find that these processes are inherently myopic in the sense that optimal strategies do not make use of future model parameters even if these are known. Finally, we argue that predictable forward preferences are a viable framework to model human‐machine interactions occurring in automated trading or robo‐advising. For both applications, we determine an optimal interaction schedule of a human agent interacting infrequently with a machine that is in charge of trading.
Machine learning (ML) models are gaining traction in securities trading because of their ability to recognize and predict patterns. This study examines how ML is transforming automated trading. ...Drawing on 213 interviews with market participants (including 94 with people working at ML-employing firms) as well as ethnographic observations of a trading firm specializing in ML-based automated trading, we argue that ML-based ('second-generation') automated trading systems are different to previous ('first-generation') automated trading systems. Where first-generation systems are based on human-defined rules, second-generation systems develop their trading rules independently. We further argue that the use of such second-generation systems prompts a rethinking of established concepts in economic sociology. In particular, a Weberian notion of social action in markets is incompatible with such systems, but we also argue that second-generation automated trading calls for a reconsideration of the notion of the performativity of financial models.
In recent years, deep reinforcement learning (Deep RL) has been successfully implemented as a smart agent in many systems such as complex games, self-driving cars, and chat-bots. One of the ...interesting use cases of Deep RL is its application as an automated stock trading agent. In general, any automated trading agent is prone to manipulations by adversaries in the trading environment. Thus studying their robustness is vital for their success in practice. However, typical mechanism to study RL robustness, which is based on white-box gradient-based adversarial sample generation techniques (like FGSM), is obsolete for this use case, since the models are protected behind secure international exchange APIs, such as NASDAQ. In this research, we demonstrate that a "gray-box" approach for attacking a Deep RL-based trading agent is possible by trading in the same stock market, with no extra access to the trading agent. In our proposed approach, an adversary agent uses a hybrid Deep Neural Network as its policy consisting of Convolutional layers and fully-connected layers. On average, over three simulated trading market configurations, the adversary policy proposed in this research is able to reduce the reward values by 214.17%, which results in reducing the potential profits of the baseline by 139.4%, ensemble method by 93.7%, and an automated trading software developed by our industrial partner by 85.5%, while consuming significantly less budget than the victims (427.77%, 187.16%, and 66.97%, respectively).
This article contains the first detailed historical study of one of the new high-frequency trading (HFT) firms that have transformed many of the world's financial markets. The study, of Automated ...Trading Desk (ATD), one of the earliest and most important such firms, focuses on how ATD's algorithms predicted share price changes. The article argues that political-economic struggles are integral to the existence of some of the 'pockets' of predictable structure in the otherwise random movements of prices, to the availability of the data that allow algorithms to identify these pockets, and to the capacity of algorithms to use these predictions to trade profitably. The article also examines the role of HFT algorithms such as ATD's in the epochal, fiercely contested shift in US share trading from 'fixed-role' markets towards 'all-to-all' markets.
Present-day securities trading is dominated by fully automated algorithms. These algorithmic systems are characterized by particular forms of knowledge risk (adverse effects relating to the use or ...absence of certain forms of knowledge) and principal-agent problems (goal conflicts and information asymmetries arising from the delegation of decision-making authority). Where automated trading systems used to be based on human-defined rules, increasingly, machine-learning (ML) techniques are being adopted to produce machine-generated strategies. Drawing on 213 interviews with market participants involved in automated trading, this study compares the forms of knowledge risk and principal-agent relations characterizing both human-defined and ML-based automated trading systems. It demonstrates that certain forms of ML-based automated trading lead to a change in knowledge risks, particularly concerning dramatically changing market settings, and that they are characterized by a lack of insight into how and why trading rules are being produced by the ML systems. This not only intensifies but also reconfigures principal-agent problems in financial markets.
•This study examines how the advent of machine learning is transforming automated securities trading.•It is argued that machine-learning systems produce new types of knowledge risk for trading firms.•The study further demonstrates that deep-learning models demand a reconsideration of principal-agent relationships.