Event Recognition Strategies applied in the Mercurio Pro ject

Abstract

Mercurio is a project currently investigated at Politecnico di Milano whose aim is to support the decision-making process of nancial investors. Mercurio identi es relevant events both from nancial news articles and nancial indexes and uses sequential pattern mining to predict exceptional events given their past occurrences and relationships with other events. The process of event recognition, both from textual and numerical data sources, is crucial to successfully reach the goals.

-

and hard to use in our context in a signi cant way. Mercurio employs a domain-speci c classi cation of articles, manually performed by our domain expert on a training set of articles, then automatically derived by the system for the remaining articles.

Communication style. Over time, companies develop a certain communication style characterized by the amount of published news, the di erent sources dealing with it, the diversity of reported topics, etc.. It is interesting to discover events where a company breaks its expected communication trend, e.g. an out-of-the-blue article breaking a \long" communication silence. Article summarization. Long articles are hardly read by investors who, instead of reading the whole news, usually skim through its content or trust little more than title and introduction. Mercurio applies summarization techniques to provide investors with only the most relevant information. It ranks each sentence in the article according to its position in the text (at the beginning, end, etc.) and to its content (domain-dependent stop-words as well as signi cant expressions are kept into account) and constructs a summary that contains only the most informative sentences.

Numerical data sources. Mercurio gathers stock prices from Yahoo! Finance 6 and employs technical analysis [ 3 ] techniques to determine signi cant events. Stock events. Mercurio identi es changes in stock using simple moving averages (sma) of di erent day lengths. For up/down trends and congestions, sma10, sma20 and sma40 are used, e.g., if the price is above sma10; sma10 is above sma20 and sma20 is above sma40 there is an ongoing uptrend. To nd up/down jumps, Mercurio analyzes how sma3 and sma5 change in a time-window of a week. All stock changes are found a posteriori and then used for training.

Candlestick patterns. Japanese candlestick charts 7 are used to represent stock prices at possibly di erent aggregation levels; speci c candlestick patterns predict particular market movements. Mercurio uses these patterns in combination with stock events to increment the precision of the event recognition. Moreover, we are investigating the use of patterns at di erent levels of aggregation, e.g. a candlesticks representing days or weeks. 6 https://finance.yahoo.com/ 7 https://en.wikipedia.org/wiki/Candlestick_pattern

References

1. S. Marchesini , M. Morlacchi Bonfanti , M. Mazuran , D. Greco , L. Tanca: Mercurio: predicting nancial events from expert knowledge and nancial news . SEBD 2016 : 174 - 181 .

2. M. Brambilla , D. Greco , S. Marchesini , L. Marconi , M. Mazuran , M. Morlacchi Bonfanti , A. Negrini , L. Tanca: Forecasting Out-of-the-Ordinary Financial Events . FINREC 2016 : 11 - 15 .

3. J. J. Murphy : Technical Analysis of the Financial Markets: A Comprehensive Guide to Trading Methods and Applications . New York Institute of Finance, 1999 .