Time series forecasting is important across various domains for decision-making. In particular, financial time series such as stock prices can be hard to predict as it is difficult to model short-term and long-term temporal dependencies between data points. Convolutional Neural Networks (CNN) are good at capturing local patterns for modeling short-term dependencies. However, CNNs cannot learn long-term dependencies due to the limited receptive field. Transformers on the other hand are capable of learning global context and long-term dependencies. In this paper, we propose to harness the power of CNNs and Transformers to model both short-term and long-term dependencies within a time series, and forecast if the price would go up, down or remain the same (flat) in the future. In our experiments, we demonstrated the success of the proposed method in comparison to commonly adopted statistical and deep learning methods on forecasting intraday stock price change of S&P 500 constituents.
Learning agent behaviors from observational data has shown to improve our understanding of their decision-making processes, advancing our ability to explain their interactions with the environment and other agents. While multiple learning techniques have been proposed in the literature, there is one particular setting that has not been explored yet: multi agent systems where agent identities remain anonymous. For instance, in financial markets labeled data that identifies market participant strategies is typically proprietary, and only the anonymous state-action pairs that result from the interaction of multiple market participants are publicly available. As a result, sequences of agent actions are not observable, restricting the applicability of existing work. In this paper, we propose a Policy Clustering algorithm, called K-SHAP, that learns to group anonymous state-action pairs according to the agent policies. We frame the problem as an Imitation Learning (IL) task, and we learn a world-policy able to mimic all the agent behaviors upon different environmental states. We leverage the world-policy to explain each anonymous observation through an additive feature attribution method called SHAP (SHapley Additive exPlanations). Finally, by clustering the explanations we show that we are able to identify different agent policies and group observations accordingly. We evaluate our approach on simulated synthetic market data and a real-world financial dataset. We show that our proposal significantly and consistently outperforms the existing methods, identifying different agent strategies.
Hawkes processes have recently risen to the forefront of tools when it comes to modeling and generating sequential events data. Multidimensional Hawkes processes model both the self and cross-excitation between different types of events and have been applied successfully in various domain such as finance, epidemiology and personalized recommendations, among others. In this work we present an adaptation of the Frank-Wolfe algorithm for learning multidimensional Hawkes processes. Experimental results show that our approach has better or on par accuracy in terms of parameter estimation than other first order methods, while enjoying a significantly faster runtime.
We study a game between liquidity provider and liquidity taker agents interacting in an over-the-counter market, for which the typical example is foreign exchange. We show how a suitable design of parameterized families of reward functions coupled with associated shared policy learning constitutes an efficient solution to this problem. Precisely, we show that our deep-reinforcement-learning-driven agents learn emergent behaviors relative to a wide spectrum of incentives encompassing profit-and-loss, optimal execution and market share, by playing against each other. In particular, we find that liquidity providers naturally learn to balance hedging and skewing as a function of their incentives, where the latter refers to setting their buy and sell prices asymmetrically as a function of their inventory. We further introduce a novel RL-based calibration algorithm which we found performed well at imposing constraints on the game equilibrium, both on toy and real market data.
We propose a novel group of Gaussian Process based algorithms for fast approximate optimal stopping of time series with specific applications to financial markets. We show that structural properties commonly exhibited by financial time series (e.g., the tendency to mean-revert) allow the use of Gaussian and Deep Gaussian Process models that further enable us to analytically evaluate optimal stopping value functions and policies. We additionally quantify uncertainty in the value function by propagating the price model through the optimal stopping analysis. We compare and contrast our proposed methods against a sampling-based method, as well as a deep learning based benchmark that is currently considered the state-of-the-art in the literature. We show that our family of algorithms outperforms benchmarks on three historical time series datasets that include intra-day and end-of-day equity stock prices as well as the daily US treasury yield curve rates.
We consider a trading marketplace that is populated by traders with diverse trading strategies and objectives. The marketplace allows the suppliers to list their goods and facilitates matching between buyers and sellers. In return, such a marketplace typically charges fees for facilitating trade. The goal of this work is to design a dynamic fee schedule for the marketplace that is equitable and profitable to all traders while being profitable to the marketplace at the same time (from charging fees). Since the traders adapt their strategies to the fee schedule, we present a reinforcement learning framework for simultaneously learning a marketplace fee schedule and trading strategies that adapt to this fee schedule using a weighted optimization objective of profits and equitability. We illustrate the use of the proposed approach in detail on a simulated stock exchange with different types of investors, specifically market makers and consumer investors. As we vary the equitability weights across different investor classes, we see that the learnt exchange fee schedule starts favoring the class of investors with the highest weight. We further discuss the observed insights from the simulated stock exchange in light of the general framework of equitable marketplace mechanism design.
Online learning of Hawkes processes has received increasing attention in the last couple of years especially for modeling a network of actors. However, these works typically either model the rich interaction between the events or the latent cluster of the actors or the network structure between the actors. We propose to model the latent structure of the network of actors as well as their rich interaction across events for real-world settings of medical and financial applications. Experimental results on both synthetic and real-world data showcase the efficacy of our approach.
Hawkes processes have recently gained increasing attention from the machine learning community for their versatility in modeling event sequence data. While they have a rich history going back decades, some of their properties, such as sample complexity for learning the parameters and releasing differentially private versions, are yet to be thoroughly analyzed. In this work, we study standard Hawkes processes with background intensity $\mu$ and excitation function $\alpha e^{-\beta t}$. We provide both non-private and differentially private estimators of $\mu$ and $\alpha$, and obtain sample complexity results in both settings to quantify the cost of privacy. Our analysis exploits the strong mixing property of Hawkes processes and classical central limit theorem results for weakly dependent random variables. We validate our theoretical findings on both synthetic and real datasets.
Market regimes is a popular topic in quantitative finance even though there is little consensus on the details of how they should be defined. They arise as a feature both in financial market prediction problems and financial market task performing problems. In this work we use discrete event time multi-agent market simulation to freely experiment in a reproducible and understandable environment where regimes can be explicitly switched and enforced. We introduce a novel stochastic process to model the fundamental value perceived by market participants: Continuous-Time Markov Switching Trending Ornstein-Uhlenbeck (CTMSTOU), which facilitates the study of trading policies in regime switching markets. We define the notion of regime-awareness for a trading agent as well and illustrate its importance through the study of different order placement strategies in the context of order execution problems.