SuperDeConFuse: A Supervised Deep Convolutional Transform based Fusion Framework for Financial Trading Systems
Indraprastha Institute of Information Technology, Delhi（德里英德拉普拉斯塔信息技术学院）；Inria Saclay（法国国家信息与自动化研究所萨克雷中心）；CentraleSupélec（巴黎中央理工-高等电力学院）；Université Gustave Eiffel（古斯塔夫·埃菲尔大学）；ESIEE Paris（巴黎高等电子工程师学院）
Pooja Gupta, Angshul Majumdar, Emilie Chouzenoux, Giovanni Chierchia
备注：
Accepted in Elsevier Expert Systems With Applications 2020
This work proposes a supervised multi-channel time-series learning framework for financial stock trading. Although many deep learning models have recently been proposed in this domain, most of them treat the stock trading time-series data as 2-D image data, whereas its true nature is 1-D time-series data. Since the stock trading systems are multi-channel data, many existing techniques treating them as 1-D time-series data are not suggestive of any technique to effectively fusion the information carried by the multiple channels. To contribute towards both of these shortcomings, we propose an end-to-end supervised learning framework inspired by the previously established (unsupervised) convolution transform learning framework. Our approach consists of processing the data channels through separate 1-D convolution layers, then fusing the outputs with a series of fully-connected layers, and finally applying a softmax classification layer. The peculiarity of our framework - SuperDeConFuse (SDCF), is that we remove the nonlinear activation located between the multi-channel convolution layers and the fully-connected layers, as well as the one located between the latter and the output layer. We compensate for this removal by introducing a suitable regularization on the aforementioned layer outputs and filters during the training phase. Specifically, we apply a logarithm determinant regularization on the layer filters to break symmetry and force diversity in the learnt transforms, whereas we enforce the non-negativity constraint on the layer outputs to mitigate the issue of dead neurons. This results in the effective learning of a richer set of features and filters with respect to a standard convolutional neural network. Numerical experiments confirm that the proposed model yields considerably better results than state-of-the-art deep learning techniques for real-world problem of stock trading.
We demonstrate the application of an algorithmic trading strategy based upon the recently developed dynamic mode decomposition (DMD) on portfolios of financial data. The method is capable of characterizing complex dynamical systems, in this case financial market dynamics, in an equation-free manner by decomposing the state of the system into low-rank terms whose temporal coefficients in time are known. By extracting key temporal coherent structures (portfolios) in its sampling window, it provides a regression to a best fit linear dynamical system, allowing for a predictive assessment of the ma…
Quantitative trading (QT), which refers to the usage of mathematical models and data-driven techniques in analyzing the financial market, has been a popular topic in both academia and financial industry since 1970s. In the last decade, reinforcement learning (RL) has garnered significant interest in many domains such as robotics and video games, owing to its outstanding ability on solving complex sequential decision making problems. RL's impact is pervasive, recently demonstrating its ability to conquer many challenging QT tasks. It is a flourishing research direction to explore RL techniques'…
Generating Alpha: A Hybrid AI-Driven Trading System Integrating Technical Analysis, Machine Learning and Financial Sentiment for Regime-Adaptive Equity Strategies
We present an agent based model of a single asset financial market that is capable of replicating several non-trivial statistical properties observed in real financial markets, generically referred to as stylized facts. While previous models reported in the literature are also capable of replicating some of these statistical properties, in general, they tend to oversimplify either the trading mechanisms or the behavior of the agents. In our model, we strived to capture the most important characteristics of both aspects to create agents that employ strategies inspired on those used in real mark…
Agent-based models, particularly those applied to financial markets, demonstrate the ability to produce realistic, simulated system dynamics, comparable to those observed in empirical investigations. Despite this, they remain fairly difficult to calibrate due to their tendency to be computationally expensive, even with recent advances in technology. For this reason, financial agent-based models are frequently validated by demonstrating an ability to reproduce well-known log return time series and central limit order book stylized facts, as opposed to being rigorously calibrated to transaction …
The art of systematic financial trading evolved with an array of approaches, ranging from simple strategies to complex algorithms all relying, primary, on aspects of time-series analysis. Recently, after visiting the trading floor of a leading financial institution, we noticed that traders always execute their trade orders while observing images of financial time-series on their screens. In this work, we built upon the success in image recognition and examine the value in transforming the traditional time-series analysis to that of image classification. We create a large sample of financial ti…
In this paper, we present a novel approach to the generation of virtual scenarios of multivariate financial data of arbitrary length and composition of assets. With this approach, decades of realistic time-synchronized data can be simulated for a large number of assets, producing diverse scenarios to test and improve quantitative investment strategies. Our approach is based on the analysis and synthesis of the time-dependent individual and joint characteristics of real financial time series, using stochastic sequences of market trends to draw multivariate returns from time-dependent probabilit…
Likelihood Lab（似然实验室）；Sun Yat-sen University（中山大学）；Peking University（北京大学）；The London School of Economics and Political Science（伦敦政治经济学院）；Tsinghua University（清华大学）
As machine learning ascends the peak of computer science zeitgeist, the usage and experimentation with sentiment analysis using various forms of textual data seems pervasive. The effect is especially pronounced in formulating securities trading strategies, due to a plethora of reasons including the relative ease of implementation and the abundance of academic research suggesting automated sentiment analysis can be productively used in trading strategies. The source data for such analyzers ranges a broad spectrum like social media feeds, micro-blogs, real-time news feeds, ex-post financial data…
University of Massachusetts Lowell（马萨诸塞大学洛厄尔分校）；GRC Capital LLC（GRC资本有限责任公司）
Financial markets are difficult to predict due to its complex systems dynamics. Although there have been some recent studies that use machine learning techniques for financial markets prediction, they do not offer satisfactory performance on financial returns. We propose a novel one-dimensional convolutional neural networks (CNN) model to predict financial market movement. The customized one-dimensional convolutional layers scan financial trading data through time, while different types of data, such as prices and volume, share parameters (kernels) with each other. Our model automatically extr…
We replicate the contested calibration of the Farmer and Joshi agent based model of financial markets using a genetic algorithm and a Nelder-Mead with threshold accepting algorithm following Fabretti. The novelty of the Farmer-Joshi model is that the dynamics are driven by trade entry and exit thresholds alone. We recover the known claim that some important stylized facts observed in financial markets cannot be easily found under calibration -- in particular those relating to the auto-correlations in the absolute values of the price fluctuations, and sufficient kurtosis. However, rather than c…
