Increasing the Explanatory Power of Investor Sentiment Analysis for Commodities in Online Media

2018 ◽  
pp. 321-332
Author(s):  
Achim Klein ◽  
Martin Riekert ◽  
Lyubomir Kirilov ◽  
Joerg Leukel
Keyword(s):  
Sentiment Analysis ◽  
Explanatory Power ◽  
Investor Sentiment ◽  
Online Media

Investor Sentiment and Flows into Treasury Funds

2018 ◽  
Keyword(s):  
Mutual Funds ◽  
Financial Market ◽  
Mutual Fund ◽  
Explanatory Power ◽  
Investor Sentiment ◽  
Fund Flows ◽  
Inflation Expectations ◽  
Relative Response ◽  
Financial Market Risk ◽  
Blue Chip

The author compares the relative response of Treasury fund flows to the sentiment-prone Michigan Survey of Inflation Expectations and to the Blue Chip Survey of Financial Forecasts, a professional forecast of inflation. The Treasury market is an ideal subject for examining whether or not sentiment affects flows: it is highly liquid, making it unlikely that it is hard to arbitrage, and inflation is the primary factor affecting its returns. Using mutual fund inflows into TIPs and Treasury mutual funds that occurred between January 1991 and June 2011, the author finds that the Michigan Survey is insignificantly related to flows into inflation-indexed TIPs and is positively related to flows into nominal Treasury funds. The Blue Chip Survey does not have incremental explanatory power. The evidence is consistent with a combination of a hedging motive and a flight to liquidity triggered by information in the Michigan Survey about households’ perception of financial market risk. The two motives reinforce each other in driving flows into nominal Treasury funds when the Michigan forecast of inflation is high, while they appear to cancel each other out in determining flows into the illiquid TIPS market.

Combined deep learning classifiers for stock market prediction: integrating stock price and news sentiments

Kybernetes ◽  
2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Shilpa B L ◽  
Shambhavi B R
Keyword(s):  
Stock Market ◽  
Sentiment Analysis ◽  
Stock Price ◽  
Moving Average ◽  
Investor Sentiment ◽  
Keyword Extraction ◽  
Stock Market Prediction ◽  
Content Type ◽  
Technical Indicator ◽  
News Sentiment

PurposeStock market forecasters are focusing to create a positive approach for predicting the stock price. The fundamental principle of an effective stock market prediction is not only to produce the maximum outcomes but also to reduce the unreliable stock price estimate. In the stock market, sentiment analysis enables people for making educated decisions regarding the investment in a business. Moreover, the stock analysis identifies the business of an organization or a company. In fact, the prediction of stock prices is more complex due to high volatile nature that varies a large range of investor sentiment, economic and political factors, changes in leadership and other factors. This prediction often becomes ineffective, while considering only the historical data or textural information. Attempts are made to make the prediction more precise with the news sentiment along with the stock price information.Design/methodology/approachThis paper introduces a prediction framework via sentiment analysis. Thereby, the stock data and news sentiment data are also considered. From the stock data, technical indicator-based features like moving average convergence divergence (MACD), relative strength index (RSI) and moving average (MA) are extracted. At the same time, the news data are processed to determine the sentiments by certain processes like (1) pre-processing, where keyword extraction and sentiment categorization process takes place; (2) keyword extraction, where WordNet and sentiment categorization process is done; (3) feature extraction, where Proposed holoentropy based features is extracted. (4) Classification, deep neural network is used that returns the sentiment output. To make the system more accurate on predicting the sentiment, the training of NN is carried out by self-improved whale optimization algorithm (SIWOA). Finally, optimized deep belief network (DBN) is used to predict the stock that considers the features of stock data and sentiment results from news data. Here, the weights of DBN are tuned by the new SIWOA.FindingsThe performance of the adopted scheme is computed over the existing models in terms of certain measures. The stock dataset includes two companies such as Reliance Communications and Relaxo Footwear. In addition, each company consists of three datasets (a) in daily option, set start day 1-1-2019 and end day 1-12-2020, (b) in monthly option, set start Jan 2000 and end Dec 2020 and (c) in yearly option, set year 2000. Moreover, the adopted NN + DBN + SIWOA model was computed over the traditional classifiers like LSTM, NN + RF, NN + MLP and NN + SVM; also, it was compared over the existing optimization algorithms like NN + DBN + MFO, NN + DBN + CSA, NN + DBN + WOA and NN + DBN + PSO, correspondingly. Further, the performance was calculated based on the learning percentage that ranges from 60, 70, 80 and 90 in terms of certain measures like MAE, MSE and RMSE for six datasets. On observing the graph, the MAE of the adopted NN + DBN + SIWOA model was 91.67, 80, 91.11 and 93.33% superior to the existing classifiers like LSTM, NN + RF, NN + MLP and NN + SVM, respectively for dataset 1. The proposed NN + DBN + SIWOA method holds minimum MAE value of (∼0.21) at learning percentage 80 for dataset 1; whereas, the traditional models holds the value for NN + DBN + CSA (∼1.20), NN + DBN + MFO (∼1.21), NN + DBN + PSO (∼0.23) and NN + DBN + WOA (∼0.25), respectively. From the table, it was clear that the RMSRE of the proposed NN + DBN + SIWOA model was 3.14, 1.08, 1.38 and 15.28% better than the existing classifiers like LSTM, NN + RF, NN + MLP and NN + SVM, respectively, for dataset 6. In addition, he MSE of the adopted NN + DBN + SIWOA method attain lower values (∼54944.41) for dataset 2 than other existing schemes like NN + DBN + CSA(∼9.43), NN + DBN + MFO (∼56728.68), NN + DBN + PSO (∼2.95) and NN + DBN + WOA (∼56767.88), respectively.Originality/valueThis paper has introduced a prediction framework via sentiment analysis. Thereby, along with the stock data and news sentiment data were also considered. From the stock data, technical indicator based features like MACD, RSI and MA are extracted. Therefore, the proposed work was said to be much appropriate for stock market prediction.

scholarly journals A New Investor Sentiment Indicator Based on Return Decomposition

2016 ◽  
Vol 4 (2) ◽  
pp. 121-130
Author(s):  
Yuan Liu ◽  
Yan Shang ◽  
Jianming Shi ◽  
Shouyang Wang
Keyword(s):  
Financial Market ◽  
Explanatory Power ◽  
Investor Sentiment ◽  
Price Impact ◽  
Idiosyncratic Volatility ◽  
Capital Asset ◽  
Return Decomposition ◽  
Daily Data ◽  
Section Model ◽  
Asset Mispricing

AbstractThis paper extends the DSSW model to accommodate rational arbitrageurs, optimistic investors and pessimistic investors. We model the price impact by using daily data and create a new methodology to calculate the optimistic and the pessimistic. The new sentiment indicator has high correlation with the other traditional ones, and as a proxy variable of individual share or financial market on daily, it could distinguish the optimistic and the pessimistic. In the empirical research, we develop a time-series model and a cross-section model respectively to explore the explanatory power of highly frequent investor sentiment to idiosyncratic volatility and capital asset mispricing. The results show that the new sentiment indicator can explain 21.31% of idiosyncratic volatility to individual share on average, and it has a great explanation of 36% to capital asset mispricing.

Revisiting Fama–French’s asset pricing model with an MCB volatility risk factor

2020 ◽  
Vol 21 (3) ◽  
pp. 233-251
Author(s):  
Xiaoying Chen ◽  
Nicholas Ray-Wang Gao
Keyword(s):  
Risk Factor ◽  
Asset Pricing ◽  
Explanatory Power ◽  
Investor Sentiment ◽  
Size Factor ◽  
Pricing Model ◽  
Volatility Risk ◽  
Content Type ◽  
Asset Pricing Model ◽  
Market Factor

Purpose Since the introduction of VIX to measure the spot volatility in the stock market, VIX and its futures have been widely considered to be the standard of underlying investor sentiment. This study aims to examine how the magnitude of contango or backwardation (MCB volatility risk factor) derived from VIX and VIX3M may affect the pricing of assets. Design/methodology/approach This paper focuses on the statistical inference of three defined MCB risk factors when cross-examined with Fama–French’s five factors: the market factor Rm–Rf, the size factor SMB (small minus big), the value factor HML (high minus low B/M), the profitability factor RMW (robust minus weak) and the investing factor CMA (conservative minus aggressive). Robustness checks are performed with the revised HML-Dev factor, as well as with daily data sets. Findings The inclusions of the MCB volatility risk factor, either defined as a spread of monthly VIX3M/VIX and its monthly MA(20), or as a monthly net return of VIX3M/VIX, generally enhance the explanatory power of all factors in the Fama and French’s model, in particular the market factor Rm–Rf and the value factor HML, and the investing factor CMA also displays a significant and positive correlation with the MCB risk factor. When the more in-time adjusted HML-Dev factor, suggested by Asness (2014), replaces the original HML factor, results are generally better and more intuitive, with a higher R2 for the market factor and more explanatory power with HML-Dev. Originality/value This paper introduces the term structure of VIX to Fama–French’s asset pricing model. The MCB risk factor identifies underlying configurations of investor sentiment. The sensitivities to this timing indicator will significantly relate to returns across individual stocks or portfolios.

Worldwide security market anomalies

1994 ◽  
Vol 347 (1684) ◽  
pp. 495-509 ◽  
Keyword(s):  
Portfolio Management ◽  
Risk Measures ◽  
Explanatory Power ◽  
Investor Sentiment ◽  
Cash Flows ◽  
Security Market ◽  
Investment Performance ◽  
Other Information ◽  
Yield Factor ◽  
Earnings Trends

Systematic violations of security market efficiency occur in equity markets because of the timing and reaction to cash flows and other information, institutional constraints and policies, and investor behaviour. They lead to significantly different risk-adjusted returns to those expected. Taking these anomalies into account provides opportunity for superior investment performance. Classifying anomalies as fundamental or seasonal differentiates between individual securities and market timing with indices. Seasonal anomalies include the January small-firm, turn-of-the-month, holiday, and day-of-the-week effects. Seasonality calendars combine the various effects to provide daily return forecasts. Fundamental anomalies include price to earnings, price to book, market capitalization, dividend yield, earnings trends and surprises, and mean reversion effects. These variables add explanatory power to that from risk measures and yield factor models to separate the best from the worst performing individual securities. Anomalies are controversial, difficult to measure and variable in time through investor sentiment and futures anticipation. Their study is interesting and challenging, and they are useful in various areas of portfolio management.

Sign in / Sign up

Export Citation Format

Share Document