Limits...
High quality topic extraction from business news explains abnormal financial market volatility.

Hisano R, Sornette D, Mizuno T, Ohnishi T, Watanabe T - PLoS ONE (2013)

Bottom Line: Understanding the mutual relationships between information flows and social activity in society today is one of the cornerstones of the social sciences.The examination of the words that are representative of the topic distributions confirms that our method is able to extract the significant pieces of information influencing the stock market.In this sense, our results prove that there is no "excess trading," when restricting to times when news is genuinely novel and provides relevant financial information.

View Article: PubMed Central - PubMed

Affiliation: ETH Zurich, Department of Management, Technology and Economics, Zurich, Switzerland. em072010@yahoo.co.jp

ABSTRACT
Understanding the mutual relationships between information flows and social activity in society today is one of the cornerstones of the social sciences. In financial economics, the key issue in this regard is understanding and quantifying how news of all possible types (geopolitical, environmental, social, financial, economic, etc.) affects trading and the pricing of firms in organized stock markets. In this article, we seek to address this issue by performing an analysis of more than 24 million news records provided by Thompson Reuters and of their relationship with trading activity for 206 major stocks in the S&P US stock index. We show that the whole landscape of news that affects stock price movements can be automatically summarized via simple regularized regressions between trading activity and news information pieces decomposed, with the help of simple topic modeling techniques, into their "thematic" features. Using these methods, we are able to estimate and quantify the impacts of news on trading. We introduce network-based visualization techniques to represent the whole landscape of news information associated with a basket of stocks. The examination of the words that are representative of the topic distributions confirms that our method is able to extract the significant pieces of information influencing the stock market. Our results show that one of the most puzzling stylized facts in financial economies, namely that at certain times trading volumes appear to be "abnormally large," can be partially explained by the flow of news. In this sense, our results prove that there is no "excess trading," when restricting to times when news is genuinely novel and provides relevant financial information.

Show MeSH

Related in: MedlinePlus

Comparison between estimated and actual trading volume.Estimated (red dashed line) and actual (black continuous line) trading volume for the four companies: (A) Toyota, (B) Yahoo, (C) Best Buy, and (D) BP. The number K of sufficient selected topics is 9 for Toyota, 4 for Yahoo, 3 for Best Buy, and 5 for BP.
© Copyright Policy
Related In: Results  -  Collection


getmorefigures.php?uid=PMC3675119&req=5

pone-0064846-g005: Comparison between estimated and actual trading volume.Estimated (red dashed line) and actual (black continuous line) trading volume for the four companies: (A) Toyota, (B) Yahoo, (C) Best Buy, and (D) BP. The number K of sufficient selected topics is 9 for Toyota, 4 for Yahoo, 3 for Best Buy, and 5 for BP.

Mentions: FIG. 5 compares the observed trading volume with the fitted trading volume using regression (2) (without the residual term ) for four stocks: Toyota, Yahoo, Best Buy, and BP. While some parts exhibit a good match, other parts show some discrepancy. To quantify the quality of the regression and explanatory power of the topic decomposition, we focus on the “peak days” previously defined and shown in Fig. 4. We define a success if the predicted volume is at least equal to 10% of the observed trading volume for a given peak day subtracting the constant value estimated via regression. The fraction of peak days among the total number peak days over the entire period from January 2003 to June 2011 whose volume is successfully accounted for in this sense is referred to as the “fraction of peaks explained” (FPE). We obtain the following values: FPE = 0.27 (the total number of explained peak days is 32 out of 119) for Toyota, FPE = 0.70 (the total number of explained peak days is 83) for Yahoo, FPE = 0.51 (the total number of explained peak days is 61) for Best Buy, and FPE = 0.43 (the total number of explained peak days is 51) for BP.


High quality topic extraction from business news explains abnormal financial market volatility.

Hisano R, Sornette D, Mizuno T, Ohnishi T, Watanabe T - PLoS ONE (2013)

Comparison between estimated and actual trading volume.Estimated (red dashed line) and actual (black continuous line) trading volume for the four companies: (A) Toyota, (B) Yahoo, (C) Best Buy, and (D) BP. The number K of sufficient selected topics is 9 for Toyota, 4 for Yahoo, 3 for Best Buy, and 5 for BP.
© Copyright Policy
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC3675119&req=5

pone-0064846-g005: Comparison between estimated and actual trading volume.Estimated (red dashed line) and actual (black continuous line) trading volume for the four companies: (A) Toyota, (B) Yahoo, (C) Best Buy, and (D) BP. The number K of sufficient selected topics is 9 for Toyota, 4 for Yahoo, 3 for Best Buy, and 5 for BP.
Mentions: FIG. 5 compares the observed trading volume with the fitted trading volume using regression (2) (without the residual term ) for four stocks: Toyota, Yahoo, Best Buy, and BP. While some parts exhibit a good match, other parts show some discrepancy. To quantify the quality of the regression and explanatory power of the topic decomposition, we focus on the “peak days” previously defined and shown in Fig. 4. We define a success if the predicted volume is at least equal to 10% of the observed trading volume for a given peak day subtracting the constant value estimated via regression. The fraction of peak days among the total number peak days over the entire period from January 2003 to June 2011 whose volume is successfully accounted for in this sense is referred to as the “fraction of peaks explained” (FPE). We obtain the following values: FPE = 0.27 (the total number of explained peak days is 32 out of 119) for Toyota, FPE = 0.70 (the total number of explained peak days is 83) for Yahoo, FPE = 0.51 (the total number of explained peak days is 61) for Best Buy, and FPE = 0.43 (the total number of explained peak days is 51) for BP.

Bottom Line: Understanding the mutual relationships between information flows and social activity in society today is one of the cornerstones of the social sciences.The examination of the words that are representative of the topic distributions confirms that our method is able to extract the significant pieces of information influencing the stock market.In this sense, our results prove that there is no "excess trading," when restricting to times when news is genuinely novel and provides relevant financial information.

View Article: PubMed Central - PubMed

Affiliation: ETH Zurich, Department of Management, Technology and Economics, Zurich, Switzerland. em072010@yahoo.co.jp

ABSTRACT
Understanding the mutual relationships between information flows and social activity in society today is one of the cornerstones of the social sciences. In financial economics, the key issue in this regard is understanding and quantifying how news of all possible types (geopolitical, environmental, social, financial, economic, etc.) affects trading and the pricing of firms in organized stock markets. In this article, we seek to address this issue by performing an analysis of more than 24 million news records provided by Thompson Reuters and of their relationship with trading activity for 206 major stocks in the S&P US stock index. We show that the whole landscape of news that affects stock price movements can be automatically summarized via simple regularized regressions between trading activity and news information pieces decomposed, with the help of simple topic modeling techniques, into their "thematic" features. Using these methods, we are able to estimate and quantify the impacts of news on trading. We introduce network-based visualization techniques to represent the whole landscape of news information associated with a basket of stocks. The examination of the words that are representative of the topic distributions confirms that our method is able to extract the significant pieces of information influencing the stock market. Our results show that one of the most puzzling stylized facts in financial economies, namely that at certain times trading volumes appear to be "abnormally large," can be partially explained by the flow of news. In this sense, our results prove that there is no "excess trading," when restricting to times when news is genuinely novel and provides relevant financial information.

Show MeSH
Related in: MedlinePlus