Positive Feedback.
DEFINITION of 'Positive Feedback'
A self-perpetuating pattern of investment behavior. The herd mentality that causes investors to sell when the market is declining and buy when it's rising is an example of positive feedback. Positive feedback is the reason why market declines often lead to further market declines and increases lead to further increases. It is also a source of market volatility. When a cycle of positive feedback continues for too long, it can create an asset bubble or a market crash.
BREAKING DOWN 'Positive Feedback'
On an individual level, positive feedback can refer to a pattern of behavior in which a positive outcome, such as executing a profitable trade, gives an investor the confidence to pursue further positive outcomes. Developing a rational trading plan and sticking to it can help investors stay confident and maintain a positive feedback loop even when they execute the inevitable losing trade.
Negative Feedback.
DEFINITION of 'Negative Feedback'
A pattern of contrarian investment behavior. An investor using a negative feedback strategy would buy stocks when prices declined and sell stocks when prices rose, which is the opposite of what most people do. Negative feedback helps make markets less volatile. Its opposite is positive feedback, in which a herd mentality pushes high prices higher and low prices lower.
BREAKING DOWN 'Negative Feedback'
On an individual level, negative feedback can refer to a pattern of behavior in which a negative outcome, such as executing a losing trade, causes an investor to question his or her skill and discourages him or her from continuing to trade. Developing a rational trading plan and sticking to it can help investors maintain confidence and avoid falling into a negative feedback loop even when they execute a losing trade.
Sentiment Feedback Strength Trading Strategy.
Genetic programming optimization for a sentiment feedback strength based trading strategy.
Steve Y. Yang, Sheung Yin Kevin Mo, AnqiLiu, Andrei A. Kirilenko A version of this paper can be found here Want to read our summaries of academic finance papers? Check out our Academic Research Insight category.
Get The Timeless Reading eBook in PDF.
Get the entire 10-part series on Timeless Reading in PDF. Save it to your desktop, read it on your tablet, or to your colleagues.
What are the research questions?
Based on the evidence that tweets are faster than news in revealing new market information, but that news is regarded a more reliable source of information, the authors propose a superior trading strategy based on the sentiment feedback strength between the news and the tweets.
By studying a total of 1,271,308 tweet messages from a selective group of users among the Twitter Financial Community ( those with the highest betweenness centrality determined to provide the most significant signal on explaining market returns) and 678,378 news articles coming from 2420 distinct providers ( via the Northern Light SinglePoint portal) on the US stock market from 2012 to 2015, they investigate whether:
Is it possible to exploit the interaction effects between two information sources, tweets and news and build a sentiment-based indicator that utilizes the concept of ‘feedback strength’ to formulate profitable trading strategies ( the benchmark is a buy and hold SP500 ETF)? Can genetic programming optimization help formulate a dynamic and adaptive (to recent market conditions) trading system?
What are the Academic Insights?
With the caveat, common to many studies exploiting unstructured data, of the short time frame studied and lack of multiple out of sample tests, they find the following:
YES - the authors find that the optimal sentiment feedback strength-based strategy combines business news articles published one day ago and tweet messages generated by the Twitter financial community two days ago. Their combination produces the best performance in terms of the Sterling ratio and the percentage of winning trades. YES-The authors conduct 1000 experiments with three groups of indicators (sentiment indicator only, combination of sentiment and technical indicators, technical indicator only) and find that the sentiment indicator only strategy is superior to both the technical indicator and the combination approach during the full period ( 2012-2015) and the out of sample period (2013-2015)
The authors include transaction costs in the analysis as well as they control for overfitting concerns.
The authors introduce a framework that exploits the ‘joint’ momentum of news and tweets sentiment. The results suggest that news and tweets sentiment can be regarded as valuable sources of information in constructing trading systems.
Future research can apply this framework on longer horizons as well as international markets to test robustness. AA has some old posts on tweets and finance here, here, and here.
The Most Important Chart from the Paper:
The results are hypothetical results and are NOT an indicator of future results and do NOT represent returns that any investor actually attained. Indexes are unmanaged, do not reflect management or trading fees, and one cannot invest directly in an index.
This study is motivated by the empirical findings that news and social media Twitter messages (tweets) exhibit persistent predictive power on financial market movement. Based on the evidence that tweets are faster than news in revealing new market information, whereas news is regarded broadly a more reliable source of information than tweets, we propose a superior trading strategy based on the sentiment feedback strength between the news and tweets using generic programming optimization method. The key intuition behind this feedback strength based approach is that the joint momentum of the two sentiment series leads to significant market signals, which can be exploited to generate superior trading profits. With the trade-off between information speed and its reliability, this study aims to develop an optimal trading strategy using investors’ sentiment feedback strength with the objective to maximize risk adjusted return measured by the Sterling ratio. We find that the sentiment feedback based strategies yield superior market returns with low maximum drawdown over the period from 2012 to 2015. In comparison, the strategies based on the sentiment feedback indicator generate over 14.7% Sterling ratio compared with 10.4% and 13.6% from the technical indicator-based strategies and the basic buy-and-hold strategy respectively. After considering transaction costs, the sentiment indicator based strategy outperforms the technical indicator based strategy consistently. Backtesting shows that the advantage is statistically significant. The result suggests that the sentiment feedback indicator provides support in controlling loss with lower maximum drawdown.
The views and opinions expressed herein are those of the author and do not necessarily reflect the views of Alpha Architect, its affiliates or its employees. Our full disclosures are available here. Definitions of common statistics used in our analysis are available here (towards the bottom). Join thousands of other readers and subscribe to our blog. This site provides NO information on our value ETFs or our momentum ETFs. Please refer to this site.
Academic Research Insight: Sentiment Feedback Strength Trading Strategy.
Academic Research Insight: Sentiment Feedback Strength Trading Strategy.
Genetic programming optimization for a sentiment feedback strength based trading strategy.
Steve Y. Yang, Sheung Yin Kevin Mo, AnqiLiu, Andrei A. Kirilenko A version of this paper can be found here Want to read our summaries of academic finance papers? Check out our Academic Research Insight category.
What are the research questions?
Based on the evidence that tweets are faster than news in revealing new market information, but that news is regarded a more reliable source of information, the authors propose a superior trading strategy based on the sentiment feedback strength between the news and the tweets.
By studying a total of 1,271,308 tweet messages from a selective group of users among the Twitter Financial Community ( those with the highest betweenness centrality determined to provide the most significant signal on explaining market returns) and 678,378 news articles coming from 2420 distinct providers ( via the Northern Light SinglePoint portal) on the US stock market from 2012 to 2015, they investigate whether:
Is it possible to exploit the interaction effects between two information sources, tweets and news and build a sentiment-based indicator that utilizes the concept of ‘feedback strength’ to formulate profitable trading strategies ( the benchmark is a buy and hold SP500 ETF)? Can genetic programming optimization help formulate a dynamic and adaptive (to recent market conditions) trading system?
What are the Academic Insights?
With the caveat, common to many studies exploiting unstructured data, of the short time frame studied and lack of multiple out of sample tests, they find the following:
YES - the authors find that the optimal sentiment feedback strength-based strategy combines business news articles published one day ago and tweet messages generated by the Twitter financial community two days ago. Their combination produces the best performance in terms of the Sterling ratio and the percentage of winning trades. YES-The authors conduct 1000 experiments with three groups of indicators (sentiment indicator only, combination of sentiment and technical indicators, technical indicator only) and find that the sentiment indicator only strategy is superior to both the technical indicator and the combination approach during the full period ( 2012-2015) and the out of sample period (2013-2015)
The authors include transaction costs in the analysis as well as they control for overfitting concerns.
Why does it matter?
The authors introduce a framework that exploits the ‘joint’ momentum of news and tweets sentiment. The results suggest that news and tweets sentiment can be regarded as valuable sources of information in constructing trading systems.
Future research can apply this framework on longer horizons as well as international markets to test robustness. AA has some old posts on tweets and finance here, here, and here.
The Most Important Chart from the Paper:
The results are hypothetical results and are NOT an indicator of future results and do NOT represent returns that any investor actually attained. Indexes are unmanaged, do not reflect management or trading fees, and one cannot invest directly in an index.
This study is motivated by the empirical findings that news and social media Twitter messages (tweets) exhibit persistent predictive power on financial market movement. Based on the evidence that tweets are faster than news in revealing new market information, whereas news is regarded broadly a more reliable source of information than tweets, we propose a superior trading strategy based on the sentiment feedback strength between the news and tweets using generic programming optimization method. The key intuition behind this feedback strength based approach is that the joint momentum of the two sentiment series leads to significant market signals, which can be exploited to generate superior trading profits. With the trade-off between information speed and its reliability, this study aims to develop an optimal trading strategy using investors’ sentiment feedback strength with the objective to maximize risk adjusted return measured by the Sterling ratio. We find that the sentiment feedback based strategies yield superior market returns with low maximum drawdown over the period from 2012 to 2015. In comparison, the strategies based on the sentiment feedback indicator generate over 14.7% Sterling ratio compared with 10.4% and 13.6% from the technical indicator-based strategies and the basic buy-and-hold strategy respectively. After considering transaction costs, the sentiment indicator based strategy outperforms the technical indicator based strategy consistently. Backtesting shows that the advantage is statistically significant. The result suggests that the sentiment feedback indicator provides support in controlling loss with lower maximum drawdown.
The views and opinions expressed herein are those of the author and do not necessarily reflect the views of Alpha Architect, its affiliates or its employees. Our full disclosures are available here. Definitions of common statistics used in our analysis are available here (towards the bottom). Join thousands of other readers and subscribe to our blog. This site provides NO information on our value ETFs or our momentum ETFs. Please refer to this site.
Like the Post? Share the Knowledge!
About the Author: Elisabetta Basilico, PhD, CFA.
Dr. Elisabetta Basilico is a seasoned investment professional with an expertise in “turning academic insights into investment strategies.” Research is her life’s work and by combing her scientific grounding in quantitative investment management with a pragmatic approach to business challenges, she’s helped several institutional investor achieve stable returns from their global wealth portfolios. Her experise spans from asset allocation to active quantitative investment strategies. Holder of the Charter Financial Analyst since 2007 and a PhD from the University of St. Gallen in Switzerland, she has experience in teaching and research at various international universities and co-author of articles published in peer-reviewed journals. She and co-author Tommi Johnsen are currently writing a book on research backed investment ideas. You can find additional information at Academic Insights on Investing.
Комментарии
Отправить комментарий