Search

Information in industry, research, and the public sector is widely stored as rendered documents (e.g., PDF files, scans). Hence, to enable downstream tasks, systems are needed that map rendered documents onto a structured hierarchical format. However, existing systems for this task are limited by heuristics and are not end-to-end trainable. In this work, we introduce the Document Structure Generator (DSG), a novel system for document parsing that is fully end-to-end trainable. DSG combines a deep neural network for parsing (i) entities in documents (e.g., figures, text blocks, headers, etc.) and (ii) relations that capture the sequence and nested structure between entities. Unlike existing systems that rely on heuristics, our DSG is trained end-to-end, making it effective and flexible for real-world applications. We further contribute a new, large-scale dataset called E-Periodica comprising real-world magazines with complex document structures for evaluation. Our results demonstrate that our DSG outperforms commercial OCR tools and, on top of that, achieves state-of-the-art performance. To the best of our knowledge, our DSG system is the first end-to-end trainable system for hierarchical document parsing., Comment: Accepted at ICDM 2023

We develop a tractable macroeconomic model that captures dynamic behaviors across multiple timescales, including business cycles. The model is anchored in a dynamic capital demand framework reflecting an interactions-based process whereby firms determine capital needs and make investment decisions at the micro level. We derive equations for aggregate demand from this micro setting and embed them in the Solow growth economy. As a result, we obtain a closed-form dynamical system with which we study economic fluctuations and their impact on long-term growth. For realistic parameters, the model has two attracting equilibria: one at which the economy contracts and one at which it expands. This bi-stable configuration gives rise to quasiperiodic fluctuations, characterized by the economy's prolonged entrapment in either a contraction or expansion mode punctuated by rapid alternations between them. We identify the underlying endogenous mechanism as a coherence resonance phenomenon. In addition, the model admits a stochastic limit cycle likewise capable of generating quasiperiodic fluctuations; however, we show that these fluctuations cannot be realized as they induce unrealistic growth dynamics. We further find that while the fluctuations powered by coherence resonance can cause substantial excursions from the equilibrium growth path, such deviations vanish in the long run as supply and demand converge., Comment: 51 pages, 19 figures

This paper suggests that business cycles may be a manifestation of coupled real economy and stock market dynamics and describes a mechanism that can generate economic fluctuations consistent with observed business cycles. To this end, we seek to incorporate into the macroeconomic framework a dynamic stock market model based on opinion interactions (Gusev et al., 2015). We derive this model from microfoundations, provide its empirical verification, demonstrate that it contains the efficient market as a particular regime and establish a link through which macroeconomic models can be attached for the study of real economy and stock market interaction. To examine key effects, we link it with a simple macroeconomic model (Blanchard, 1981). The coupled system generates nontrivial endogenous dynamics, which exhibit deterministic and stochastic features, producing quasiperiodic fluctuations (business cycles). We also inspect this system's behavior in the phase space. The real economy and the stock market coevolve dynamically along the path governed by a stochastically-forced dynamical system with two stable equilibria, one where the economy expands and the other where it contracts, resulting in business cycles identified as the coherence resonance phenomenon. Thus, the incorporation of stock market dynamics into the macroeconomic framework, as presented here, allows the derivation of realistic behaviors in a tractable setting., Comment: 54 pages

In this paper we seek to demonstrate the predictability of stock market returns and explain the nature of this return predictability. To this end, we introduce investors with different investment horizons into the news-driven, analytic, agent-based market model developed in Gusev et al. (2015). This heterogeneous framework enables us to capture dynamics at multiple timescales, expanding the model's applications and improving precision. We study the heterogeneous model theoretically and empirically to highlight essential mechanisms underlying certain market behaviors, such as transitions between bull- and bear markets and the self-similar behavior of price changes. Most importantly, we apply this model to show that the stock market is nearly efficient on intraday timescales, adjusting quickly to incoming news, but becomes inefficient on longer timescales, where news may have a long-lasting nonlinear impact on dynamics, attributable to a feedback mechanism acting over these horizons. Then, using the model, we design algorithmic strategies that utilize news flow, quantified and measured, as the only input to trade on market return forecasts over multiple horizons, from days to months. The backtested results suggest that the return is predictable to the extent that successful trading strategies can be constructed to harness this predictability., Comment: This is the version accepted for publication in a journal Quantitative Finance. A draft was posted here on 18 August 2015. 50 pages

We attempt to explain stock market dynamics in terms of the interaction among three variables: market price, investor opinion and information flow. We propose a framework for such interaction and apply it to build a model of stock market dynamics which we study both empirically and theoretically. We demonstrate that this model replicates observed market behavior on all relevant timescales (from days to years) reasonably well. Using the model, we obtain and discuss a number of results that pose implications for current market theory and offer potential practical applications., Comment: This is the version accepted for publication in a new journal Algorithmic Finance (http://algorithmicfinance.org). A draft was posted here on 29 April