The dynamics of cryptocurrency market behavior: sentiment analysis using Markov chains

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Kwansoo Kim ◽  
Sang-Yong Tom Lee ◽  
Saïd Assar
Keyword(s):  
Markov Model ◽  
Design Methodology ◽  
Unobserved Heterogeneity ◽  
Hidden Markov ◽  
Market Behavior ◽  
Content Type ◽  
Bear Market ◽  
Increasing Trend ◽  
Hidden States ◽  
Bull And Bear Markets

PurposeThe authors examine cryptocurrency market behavior using a hidden Markov model (HMM). Under the assumption that the cryptocurrency market has unobserved heterogeneity, an HMM allows us to study (1) the extent to which cryptocurrency markets shift due to interactions with social sentiment during a bull or bear market and (2) the heterogeneous pattern of cryptocurrency market behavior under these two market conditions.Design/methodology/approachThe authors advance the HMM model based on two six-month datasets (from November 2017 to April 2018 for a bull market and from December 2018 to May 2019 for a bear market) collected from Google, Twitter, the stock market and cryptocurrency trading platforms in South Korea. Social sentiment data were collected by crawling Bitcoin-related posts on Twitter.FindingsThe authors highlight the reaction of the cryptocurrency market to social sentiment under a bull and a bear market and in two hidden states (an upward and a downward trend). They find: (1) social sentiment is relatively relevant during a bull compared to a bear market. (2) The cryptocurrency market in a downward state, that is, with a local decreasing trend, tends to be more responsive to positive social sentiment. (3) The market in an upward state, that is, with a local increasing trend, tends to better interact with negative social sentiment.Originality/valueThe proposed HMM model contributes to a theoretically grounded understanding of how cryptocurrency markets respond to social sentiment in bull and bear markets through varied sequences adjusted for cryptocurrency market heterogeneity.

Remaining Useful Life Estimation Based on a Segmental Hidden Markov Model With Continuous Observations

2017 ◽  
Author(s):  
Zhen Chen ◽  
Tangbin Xia ◽  
Ershun Pan
Keyword(s):  
Markov Model ◽  
Hidden Markov Model ◽  
Goodness Of Fit ◽  
Hidden Markov ◽  
Remaining Useful Life ◽  
Likelihood Method ◽  
Distribution Model ◽  
Unknown Parameters ◽  
Useful Life ◽  
Hidden States

In this paper, a segmental hidden Markov model (SHMM) with continuous observations, is developed to tackle the problem of remaining useful life (RUL) estimation. The proposed approach has the advantage of predicting the RUL and detecting the degradation states simultaneously. As the observation space is discretized into N segments corresponding to N hidden states, the explicit relationship between actual degradation paths and the hidden states can be depicted. The continuous observations are fitted by Gaussian, Gamma and Lognormal distribution, respectively. To select a more suitable distribution, model validation metrics are employed for evaluating the goodness-of-fit of the available models to the observed data. The unknown parameters of the SHMM can be estimated by the maximum likelihood method with the complete data. Then a recursive method is used for RUL estimation. Finally, an illustrate case is analyzed to demonstrate the accuracy and efficiency of the proposed method. The result also suggests that SHMM with observation probability distribution which is closer to the real data behavior may be more suitable for the prediction of RUL.

The impact of Mad Money recommendations during bull and bear markets

2016 ◽  
Vol 12 (1) ◽  
pp. 52-70 ◽  
Author(s):  
Adam J. Roszkowski ◽  
Nivine Richie
Keyword(s):  
Prospect Theory ◽  
Behavioral Finance ◽  
Abnormal Returns ◽  
Good News ◽  
Content Type ◽  
Bear Market ◽  
Bear Markets ◽  
The Impact ◽  
Investor Reaction ◽  
Bull And Bear Markets

Purpose – The purpose of this paper is to examine semi-strong market efficiency by observing the behavioral finance implications of Jim Cramer’s recommendations in bull vs bear markets. The authors extend the literature by analyzing investor reaction through the lenses of prospect theory, overreaction, and herding. Design/methodology/approach – The authors test for abnormal returns in response to Mad Money buy and sell recommendations. The authors use a sample of buy and sell recommendations from MadMoneyRecap.com from July 28, 2005 through February 9, 2009. The 3.5-year time period is the most recent and comprehensive set of Mad Money recommendations that has been tested to date. Findings – The results indicate market inefficiency at the semi-strong level. Furthermore, the findings highlight the loss aversion tendencies of investors in regards to prospect theory of Kahneman and Tversky (1979) as well as the disposition effect of Shefrin and Statman (1985). Evidence also exists consistent with the herding and overreaction hypotheses. Practical implications – The evidence suggests contrarian behavior in which investors respond positively to good news in bad times – perhaps, in effort to stay the course and at least break even. This behavior may suggest that losers tend to hold on to losses in hopes of recouping them. Thus, positive information in bad times could further persuade market participants to hang on to or buy more of losers, while also persuading non-shareholders to buy in as well. Originality/value – Though other studies including Kenny and Johnson (2010) have estimated abnormal returns in response to analyst recommendations, to the knowledge, none has examined behavioral implications of investor reaction to buy and sell recommendations in both bull and bear markets. Furthermore, the study captures a longer bull and bear market and covers two definitions of such markets.

scholarly journals Forecasting violent events in the Middle East and North Africa using the Hidden Markov Model and regularized autoregressive models

2018 ◽  
Vol 17 (3) ◽  
pp. 269-283
Author(s):  
KSM Tozammel Hossain ◽  
Shuyang Gao ◽  
Brendan Kennedy ◽  
Aram Galstyan ◽  
Prem Natarajan
Keyword(s):  
Markov Model ◽  
Hidden Markov Model ◽  
Hidden Markov ◽  
Lead Times ◽  
External Data ◽  
Two Cities ◽  
Data Capturing ◽  
Action Type ◽  
Statistical Time ◽  
Hidden States

This paper focuses on forecasting Military Action-type events by both state and non-state actors. Here we demonstrate that the dynamics of these types of events can be adequately described by a Hidden Markov Model (HMM) where the hidden states correspond to different operational regimes of an actor, and observations correspond to event frequency—and the HMM effectively predicts events with different lead times. We also demonstrate that one can enrich statistical time series-based methods that work only on historical data by exploiting predictive signals in real-time external data streams. We demonstrate the superior predictive power of the proposed models with evaluation of recent data capturing activities over two groups, ISIS and the Syrian Arab Military, two countries, Syria and Iraq, and two cities, Aleppo and Mosul. We also present an approach to converting predictions of the proposed models to real-world warnings.

Impact of plasticity generated by Rayleigh waves on the residual stress behavior of structural components subjected to laser peening

2015 ◽  
Vol 6 (1) ◽  
pp. 107-123 ◽  
Author(s):  
Anoop Vasu ◽  
Ramana V. Grandhi
Keyword(s):  
Residual Stress ◽  
Rayleigh Waves ◽  
Design Methodology ◽  
Laser Peening ◽  
Structural Components ◽  
Wave Mechanics ◽  
Content Type ◽  
Analytical Formulation ◽  
Increasing Trend ◽  
The Impact

Purpose – The impact of laser peening on curved geometries is not fully comprehended. The purpose of this paper is to explain the action of laser peening on curved components (concave and convex shapes for cylindrical and spherical geometries) by means of shock wave mechanics. Design/methodology/approach – An analytical formulation is derived based on the plasticity incurred inside the material and the results are compared with the prediction by numerical simulation. Findings – A near-linear relationship is observed between curvature and compressive residual stress; an increasing trend was observed for concave models and a decreasing trend was observed for convex models. The consistency in the analytical formulation with the simulation model indicates the behavior of laser peening for curved geometries. Originality/value – The differences observed in the residual stresses for spherical and cylindrical geometries are primarily due to the effect of Rayleigh waves. This paper illustrates the importance of understanding the physics behind laser peening of curved geometries.

Fuzzy Markov development for buried transportation bridges

2019 ◽  
Vol 11 (2) ◽  
pp. 338-353 ◽  
Author(s):  
Koorosh Gharehbaghi ◽  
Kerry McManus ◽  
Kathryn Robson ◽  
Chris Eves ◽  
Matt Myers
Keyword(s):  
Markov Model ◽  
Design Methodology ◽  
Structural Integrity ◽  
Transition Probability ◽  
Warning Signs ◽  
Buried Structures ◽  
Content Type ◽  
Early Warning Signs ◽  
Age Dependent ◽  
Inspection And Maintenance

Purpose The purpose of this paper is to review the Fuzzy Markov development for assessing the structural integrity of buried transportation bridges. In doing so, the appropriateness of Fuzzy Markov will be assessed, leading to the subsequent model. Design/methodology/approach This research will utilize the Fuzzy Markov techniques as the conceptual framework. Such methodology is further supported via the utilization and evaluation of 30 buried transportation bridges using the developed Fuzzy Markov model. Findings Subsequently, through a developed Fuzzy Markov model, this research found that as the basis of structural resilience, specific matrices for age-dependent transition probability can be compiled using conditional survival probabilities in the various structural states; as the basis of structural integrity, specific environmental and economic schemes can also be established based on inspection intervals, intervention systems and failure phases; exact inspection and maintenance intervals can be scheduled to further prolong an asset’s life; and clear and early warning signs can also be formulated for immediate intervention when the structural integrity of the asset are indeed compromised. Originality/value The gap within the literature currently surrounds the limitation of computational analysis for some buried structures such as bridges. Specifically, to streamline such evaluation and regimes, a Fuzzy Markov is developed and reviewed.

Predicting the effect of Googling investor sentiment on Islamic stock market returns

2020 ◽  
Vol 13 (2) ◽  
pp. 165-193
Author(s):  
Yousra Trichilli ◽  
Mouna Boujelbène Abbes ◽  
Afif Masmoudi
Keyword(s):  
Stock Market ◽  
Markov Model ◽  
Financial Markets ◽  
Hidden Markov Model ◽  
Hidden Markov ◽  
Investor Sentiment ◽  
Market Returns ◽  
Stock Market Returns ◽  
Content Type ◽  
The Relationship

Purpose The purpose of this paper is to evaluate the capability of the hidden Markov model using Googling investors’ sentiments to predict the dynamics of Islamic indexes’ returns in the Middle East and North Africa (MENA) financial markets from 2004 to 2018. Design/methodology/approach The authors propose a hidden Markov model based on the transition matrix to apprehend the relationship between investor’s sentiment and Islamic index returns. The proposed model facilitates capturing the uncertainties in Islamic market indexes and the possible effects of the dynamics of Islamic market on the persistence of these regimes or States. Findings The bearish state is the most persistent sentiment with the longest duration for all the MENA Islamic markets except for Jordan, Morocco and Qatar. In addition, the obtained results indicate that the effect of sentiment on predicting the future Islamic index returns is conditional on the MENA States. Besides, the estimated mean returns for each state indicates that the bullish and calm states are ideal for investing in Islamic indexes of Bahrain, Oman, Morocco, Kuwait, Saudi Arabia and United Arab Emirates. However, only the bullish state is ideal for investing Islamic indexes of Jordan, Egypt and Qatar. Research limitations/implications This paper has used data at a monthly frequency that can explain only short-term dynamics between Googling investor’s sentiment and the MENA Islamic stock market returns. Moreover, this work can be done on the stock markets while taking into account the specificity of each activity sector. Practical implications In fact, the findings of this paper are helpful for academics, analysts and practitioners, and more specifically for the Islamic MENA financial investors. Moreover, this study provides useful insights not only into the duration of the relationship between the indexes’ returns and the investors’ sentiments in the five states but also into the transition probabilities which have implications for how investors could be guided in their choice of future investment in a portfolio with Islamic indexes. Findings of this paper are important and valuable for policy-makers and investors. Thus, predicting the effect of Googling investors’ sentiment on the MENA Islamic stock market dynamics is important for portfolio diversification by domestic and international investors. Moreover, the results of this paper gave new insights into financial analysts about the dynamic relationship between Googling investors’ sentiment and Islamic stock market returns across market regimes. Therefore, the findings of this study might be useful for investors as they help them capture the unobservable dynamics of the changes in the investors’ sentiment regimes in the MENA financial markets to make successful investment decisions. Originality/value To the best of the authors’ knowledge, this paper is the first to use the hidden Markov model to examine changes in the Islamic index return dynamics across five market sentiment states, namely the depressed sentiment (S1), the bullish sentiment (S2), the bearish sentiment (S3), the calm sentiment (S4) and the bubble sentiment (S5).

Relevance and evolution of adaptive markets hypothesis: a review

2016 ◽  
Vol 8 (3) ◽  
pp. 166-179 ◽  
Author(s):  
Raj S. Dhankar ◽  
Devesh Shankar
Keyword(s):  
Stock Market ◽  
Stock Markets ◽  
Design Methodology ◽  
Efficient Market Hypothesis ◽  
Efficient Markets ◽  
Informational Efficiency ◽  
Market Behavior ◽  
Efficient Market ◽  
Content Type ◽  
Dynamic Perspective

Purpose The purpose of this paper is to discuss the relevance and evolution of adaptive markets hypothesis (AMH) that has gained traction in the recent years, as it provides a dynamic perspective to the concept of informational efficiency. Design/methodology/approach This paper discusses several issues related to the concept of informationally efficient markets that have indicated efficient market hypothesis to be an incomplete portrayal of stock market behavior. Findings The authors find that a strict and perpetual adherence to informational efficiency is highly unlikely, and AMH provides a much more plausible description of the behavior of stock markets. Originality/value The authors provide a description of studies that examine the testable implications of AMH.

scholarly journals Hidden Markov Model

d'CARTESIAN ◽  
2015 ◽  
Vol 4 (1) ◽  
pp. 86 ◽  
Author(s):  
Kezia Tumilaar ◽  
Yohanes Langi ◽  
Altien Rindengan
Keyword(s):  
Markov Model ◽  
Hidden Markov Model ◽  
Viterbi Algorithm ◽  
Markov Models ◽  
Hidden Markov ◽  
Learning Problem ◽  
Model Learning ◽  
Observation Sequence ◽  
Evaluation Problem ◽  
Hidden States

Hidden Markov Models (HMM) is a stochastic model and is essentially an extension of Markov Chain. In Hidden Markov Model (HMM)  there are two types states: the observable states and the hidden states. The purpose of this research are to understand how hidden Markov model (HMM) and to understand how the solution of three basic problems on Hidden Markov Model (HMM) which consist of evaluation problem, decoding problem and learning problem.  The result of the research is hidden Markov model can be defined as . The evaluation problem or to compute probability of the observation sequence given the model P(O|) can solved  by Forward-Backward algorithm, the decoding problem or to choose hidden state sequence which is optimal can solved by Viterbi algorithm and learning problem or to estimate hidden Markov model parameter  to maximize P(O|)  can solved by Baum – Welch algorithm. From description above Hidden Markov Model  with state 3  can describe behavior  from the case studies. Key  words: Decoding Problem, Evaluation Problem, Hidden Markov Model, Learning Problem

Cyclicity of real estate-related trends: topic modelling and sentiment analysis on German real estate news

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Franziska Ploessl ◽  
Tobias Just ◽  
Lino Wehrheim
Keyword(s):  
Real Estate ◽  
Design Methodology ◽  
News Coverage ◽  
Topic Modelling ◽  
Content Type ◽  
Increasing Trend ◽  
Word Representation ◽  
Negative Sentiment ◽  
Newspaper Articles

PurposeThe purpose of this paper is to identify and analyse the news coverage and sentiment of real estate-related trends in Germany. Trends are considered as being stable and long-term. If the news coverage and sentiment of trends underlie cyclicity, this could impact investors’ behaviour. For instance, in the case of increased reporting on sustainability issues, investors may be inclined to invest more in sustainable buildings, assuming that this is of growing importance to their clients. Hence, investors could expect higher returns when a trend topic goes viral.Design/methodology/approachWith the help of topic modelling, incorporating seed words partially generated via word embeddings, almost 170,000 newspaper articles published between 1999 and 2019 by a major German real estate news provider are analysed and assigned to real estate-related trends. Through applying a dictionary-based approach, this dataset is then analysed based on whether the tone of the news coverage of a specific trend is subject to change.FindingsThe articles concerning urbanisation and globalisation account for the largest shares of reporting. However, the shares are subject to change over time, both in terms of news coverage and sentiment. In particular, the topic of sustainability illustrates a clearly increasing trend with cyclical movements throughout the examined period. Overall, the digitalisation trend has a highly positive connotation within the analysed articles, while regulation displays the most negative sentiment.Originality/valueTo the best of the authors’ knowledge, this is the first application to explore German real estate newspaper articles regarding the methodologies of word representation and seeded topic modelling. The integration of topic modelling into real estate analysis provides a means through which to extract information in a standardised and replicable way. The methodology can be applied to several further fields like analysing market reports, company statements or social media comments on real estate topics. Finally, this is also the first study to measure the cyclicity of real estate-related trends by means of textual analysis.

Sign in / Sign up

Export Citation Format

Share Document