scholarly journals Latent Segmentation of Stock Trading Strategies Using Multi-Modal Imitation Learning

2020 ◽  
Vol 13 (11) ◽  
pp. 250
Author(s):  
Iwao Maeda ◽  
David deGraw ◽  
Michiharu Kitano ◽  
Hiroyasu Matsushima ◽  
Kiyoshi Izumi ◽  
...  
Keyword(s):  
Stock Exchange ◽  
Trading Strategies ◽  
Imitation Learning ◽  
Stock Trading ◽  
Reward Function ◽  
Market Participants ◽  
Individual Market ◽  
Reward Functions ◽  
Real Market ◽  
The Individual

While exchanges and regulators are able to observe and analyze the individual behavior of financial market participants through access to labeled data, this information is not accessible by other market participants nor by the general public. A key question, then, is whether it is possible to model individual market participants’ behaviors through observation of publicly available unlabeled market data alone. Several methods have been suggested in the literature using classification methods based on summary trading statistics, as well as using inverse reinforcement learning methods to infer the reward function underlying trader behavior. Our primary contribution is to propose an alternative neural network based multi-modal imitation learning model which performs latent segmentation of stock trading strategies. As a result that the segmentation in the latent space is optimized according to individual reward functions underlying the order submission behaviors across each segment, our results provide interpretable classifications and accurate predictions that outperform other methods in major classification indicators as verified on historical orderbook data from January 2018 to August 2019 obtained from the Tokyo Stock Exchange. By further analyzing the behavior of various trader segments, we confirmed that our proposed segments behaves in line with real-market investor sentiments.

scholarly journals Möglichkeiten und Grenzen der Analyse von Holzmärkten

2012 ◽  
Vol 163 (10) ◽  
pp. 396-400 ◽  
Author(s):  
Roland Olschewski ◽  
Oliver Thees
Keyword(s):  
State Of The Art ◽  
Agent Based Modeling ◽  
Behavioural Economics ◽  
Future Market ◽  
Individual Behaviour ◽  
Agent Based ◽  
Market Participants ◽  
Real Market ◽  
The Individual ◽  
Forest Economic

Chances and limits of the analysis of wood markets Recent approaches of behavioural economics and agent-based modeling can enhance knowledge about market processes and results and widen the focus for the assessment of future market developments by emphasising the individual behaviour of market participants and scenario techniques. In this article we resume possible contributions of the particular approaches to better describe, explain and forecast real market developments. The exposition is based on state-of-the-art knowledge and reflects insights gained during the 8th Forest Economic Seminar in autumn 2011, where researchers and practitioners presented their findings.

scholarly journals Management discussion and analysis, corporate governance perception index and market reaction

2017 ◽  
Vol 14 (4) ◽  
pp. 165-175
Author(s):  
Lindrianasari Lindrianasari ◽  
Sondang Berliana Gultom ◽  
Liza Alvia
Keyword(s):  
Corporate Governance ◽  
Stock Returns ◽  
Capital Market ◽  
Trading Volume ◽  
Market Reaction ◽  
Stock Exchange ◽  
Volume Activity ◽  
Stock Trading ◽  
Market Participants ◽  
Investor Reaction

This research generally aims to provide empirical evidence on investor reaction to the disclosure of Management’s Discussion and Analysis of the companies listed on the Indonesia Stock Exchange in the period of 2011-2013. The motivation of this study is that there is no study in Indonesia concerning the presentation of the Management’s Discussion and Analysis that affect investors’ decision to invest in an enterprise, which is illustrated by the market reaction to stock returns and trading volume activity. There are 827 samples in this study in the period of 2011-2013. This study found that Indonesian capital market is responding to the disclosure of Management’s Discussion and Analysis provided by the company. The more complete disclosure of the information in the Management’s Discussion and Analysis, the better the market response. Corporate Governance Perception Index also responded positively and significantly to the stock trading volume. These findings indicate that the disclosure of information contained in Management’s Discussion and Analysis and Corporate Governance Perception Index utilised for market participants in Indonesia in decision-making.

The Role of Institutional Traders around Section Switches on the Tokyo Stock Exchange

1998 ◽  
Vol 01 (02) ◽  
pp. 233-251
Author(s):  
Asjeet S. Lamba ◽  
Mohamed Ariff
Keyword(s):  
Mutual Funds ◽  
Trading Volume ◽  
Stock Exchange ◽  
Abnormal Returns ◽  
Trading Strategies ◽  
Trading Behavior ◽  
Buying Behavior ◽  
Market Participants ◽  
Major Market ◽  
Tokyo Stock Exchange

In this paper we analyze the trading behavior of major market participants around switches from section 2 to section 1 of the Tokyo Stock Exchange (TSE). Previous research has shown that firms switching to section 1 earn significant positive abnormal returns around the switch date. It has been argued that the abnormal returns earned by these firms are driven by the trading strategies of a few large mutual funds that dominate trading on the TSE. If these large mutual funds have prior information about impending switches, and are exploiting this information, their trading strategies would be more obvious in periods when a large number of firms switch to section 1. Based on the observation that a much larger proportion of firms switch to section 1 in September than in other months, we examine the pricing and trading volume behavior of firms switching to section 1 in September and other months during the years 1984–1992. We find significantly higher abnormal returns for firms switching in September than in other months. Also, firms switching in September experience a significant and persistent increase in excess trading volume compared with firms switching in other months. Taken in conjunction with the abnormal return results, this evidence is consistent with a persistent buying behavior on the part of large mutual funds prior to an impending switch to section 1.

Management control systems in the knowledge economy: Assessing the role of intellectual capital in

2020 ◽  
pp. 17-34
Author(s):  
Federica Ricci ◽  
Vincenzo Scafarto ◽  
Salvatore Ferri ◽  
Teresa Riso
Keyword(s):  
Intellectual Capital ◽  
Firm Value ◽  
Stock Exchange ◽  
Value Added ◽  
Management Control ◽  
Market Participants ◽  
Stock Market Performance ◽  
Other Information ◽  
External Reporting ◽  
The Individual

The purpose of this paper is to show that intellectual capital (IC) efficiency as measured by the value added intellectual coefficient (VAIC) and its individual components may function as key performance indicators for use in management control and external reporting to capital market participants. We incorporate the VAIC within the Ohlson model (OM), a widely used model for equity valuation, which relates a firm's market value to the book value of equity and net earnings, and allows to include any other information that may affect the market assess-ment of firm value. We then estimate the modified OM on a panel sample of firms continuously listed on the Italian Stock exchange from 2011 to 2017 using a fixed effect (FE) specification. Empirical results indicate that IC efficiency contributes along with the traditional accounting metrics included in the OM to explain the stock market performance of sample firms. This paper suggests that the VAIC and the individual measures of IC efficiency may usefully complement traditional accounting measures of performance.

scholarly journals Control-Stopping Games for Market Microstructure and Beyond

2020 ◽  
Vol 45 (4) ◽  
pp. 1289-1317
Author(s):  
Roman Gayduk ◽  
Sergey Nadtochiy
Keyword(s):  
Market Microstructure ◽  
Value Functions ◽  
Existence Of A Solution ◽  
Reward Function ◽  
Potential Applications ◽  
Fundamental Value ◽  
Reward Functions ◽  
The Individual ◽  
Stopping Games ◽  
Reflecting Barriers

In this paper, we present a family of control-stopping games that arise naturally in equilibrium-based models of market microstructure as well as in other models with strategic buyers and sellers. A distinctive feature of this family of games is the fact that the agents do not have any exogenously given fundamental value for the asset, and they deduce the value of their position from the bid and ask prices posted by other agents (i.e., they are pure speculators). As a result, in such a game, the reward function of each agent at the time of stopping depends directly on the controls of other players. The equilibrium problem leads naturally to a system of coupled control-stopping problems (or, equivalently, reflected-backward stochastic differential equations), in which the individual reward functions (or reflecting barriers) depend on the value functions (or solution components) of other agents. The resulting system, in general, presents multiple mathematical challenges because of the nonstandard form of coupling (or reflection). In the present case, this system is also complicated by the fact that the continuous controls of the agents, describing their posted bid and ask prices, are constrained to take values in a discrete grid. The latter feature reflects the presence of a positive tick size in the market, and it creates additional discontinuities in the agents’ reward functions (or reflecting barriers). Herein we prove the existence of a solution to the associated system in a special Markovian framework, provide numerical examples, and discuss the potential applications.

PENGARUH FREKUENSI PERDAGANGAN PADA SEKTOR PROPERTY DAN REAL ESTATE TERHADAP HARGA SAHAM

2019 ◽  
Vol 7 (02) ◽  
pp. 51
Author(s):  
Adri Wihananto
Keyword(s):  
Real Estate ◽  
Stock Price ◽  
Stock Exchange ◽  
Stock Trading ◽  
Trading Frequency ◽  
Important Thing ◽  
Know How ◽  
Stock Value ◽  
Measuring Frequency ◽  
Case Based

Trading frequency can be said as the implementation from trader of commerce. This case based on positive or negative trader reaction given by trader information.  Stock trading in BEI always fluctuate with price of volume value and frequency particularly. Frequency itself shows the company  involved or not. In trading frequency, if the indicator frequency it self shown the higher point, it means better. In spite of the most important thing is how the fluctuation or value conversion itself. On the frequencies we also could see which stocks is interested by the investor. When trading frequency high, it  may be create sense of interest from investors.The aim of this research, in order to know how far the effect of trading frequency (X) with stock value (Y) using cover stock value. The information used is begin 2008 with sample from twelve property and real estate companies. According to the research can be conclude from twelve companies in Indonesia Stock Exchange in 2008, 75 % of trading frequency samples doesn’t have signification degree between trading frequency and stock value. This case can be explained count on smaller than t tableEvaluation of this research is the trading measuring frequency at property sector and real estate not influence to stock priceKeywords : Trading Frequency, Stock Price 

Adaptive stock trading strategies with deep reinforcement learning methods

2020 ◽  
Vol 538 ◽  
pp. 142-158 ◽  
Author(s):  
Xing Wu ◽  
Haolei Chen ◽  
Jianjia Wang ◽  
Luigi Troiano ◽  
Vincenzo Loia ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Trading Strategies ◽  
Stock Trading ◽  
Learning Methods

Expanding Coverage: Maintain A Role For The Individual Market

2002 ◽  
Vol 21 (Suppl1) ◽  
pp. W391-W394 ◽  
Author(s):  
Donald A. Young ◽  
Thomas F. Wildsmith
Keyword(s):  
Individual Market ◽  
The Individual

scholarly journals MARKET STATISTICS OF A PSYCHOLOGY-BASED HETEROGENEOUS AGENT MODEL

2008 ◽  
Vol 11 (07) ◽  
pp. 717-737 ◽  
Author(s):  
HARBIR LAMBA ◽  
TIM SEAMAN
Keyword(s):  
Heterogeneous Agent ◽  
Agent Based ◽  
Agent Model ◽  
Fundamental Parameters ◽  
Market Participants ◽  
Information Stream ◽  
Momentum Trading ◽  
Real Market ◽  
Available Information ◽  
Parameter Values

We continue an investigation into a class of agent-based market models that are motivated by a psychologically-plausible form of bounded rationality. Some of the agents in an otherwise efficient hypothetical market are endowed with differing tolerances to the tension caused by being in the minority. This herding tendency may be due to purely psychological effects, momentum-trading strategies, or the rational response to perverse marketplace incentives. The resulting model has the important properties of being both very simple and insensitive to its small number of fundamental parameters. While it is most certainly a caricature market, with only boundedly rational traders and the globally available information stream being modeled directly, other market participants and effects are indirectly replicated. We show that all of the most important "stylized facts" of real market statistics are reproduced by this model. Another useful aspect of the model is that, for certain parameter values, it reduces to a standard efficient-market system. This allows us to isolate and observe the effects of particular kinds of non-rationality. To this end, we consider the effects of different asymmetries in agent behavior and show that one in particular leads to skew statistics consistent with those seen in some real financial markets.

scholarly journals Does the Croatian Stock Market Have Seasonal Affective Disorder?

2021 ◽  
Vol 14 (2) ◽  
pp. 89
Author(s):  
Tihana Škrinjarić ◽  
Branka Marasović ◽  
Boško Šego
Keyword(s):  
Stock Market ◽  
Stock Returns ◽  
Affective Disorder ◽  
Seasonal Affective Disorder ◽  
Stock Exchange ◽  
Trading Strategies ◽  
Future Research ◽  
Winter Solstice ◽  
Daily Data ◽  
Depressive Episodes

This paper explores mood anomalies, specifically the seasonal affective disorder (SAD) effect on the Zagreb Stock Exchange (ZSE). SAD is defined as a syndrome of depressive episodes in human behavior due to the changing of the season. Thus, the motive of this research is to gain better insights into the investors’ sentiment regarding SAD effects. The purpose of the research is to observe how investors’ sentiment affects the return and risk series on ZSE and if this could be exploitable. Using daily data on stock market return CROBEX for the period January 2010—February 2021, SAD effects are tested to explore if seasonal changes affect the stock returns and risk. Besides the SAD variable in the model, some control variables are included as well: Monday, tax, and COVID-19 effect. The results indicate that SAD effects exist on ZSE, even with controlling for mentioned effects; and asymmetries around winter solstice exist. Implications of such findings can be found in simulating trading strategies, which could incorporate such information to gain profits. Limitations of the research focus on one market, observing static parameters of the estimated models, and observing simple trading strategies. Thus, future research should focus on international diversification possibilities, time-varying models, and fully exploring the exploitation possibilities of such findings.

Sign in / Sign up

Export Citation Format

Share Document