Reading the Markets: Forecasting Prediction Markets By News Content Analysis

نویسندگان

  • Ari Gilder
  • Kevin Lerman
  • Fernando Pereira
  • Mark Dredze
چکیده

Our results as a percentage of maximum possible earnings (if correct decisions were made every day). Combined/parsing (our final system) is roughly equal to the sum of its two constituent systems’ performance. Note: Weather Forecasting is our baseline that assumes yesterday’s price trend will continue. 5.2% 11.4% 2.7% 12.5% 4.3% 16.0% AVERAGE 1.7% -0.5% -12.6% 3.7% -18.5% 1.9% Lieberman 6.2% 8.6% 7.5% -5.5% 8.4% 20.6% Kerry 0.4% 12.7% 0.9% 8.0% 2.9% 7.9% Gephardt 23.9% 34.4% 40.7% 23.5% 35.1% 29.9% Dean -7.8% 13.9% -12.0% 37.7% -10.5% 23.9% Clinton 12.9% 14.7% 14.5% 20.3% 6.2% 15.2% Clark 14.9% -3.4% 11.2% 2.0% 20.5% 13.3% Kerry (election) 19.8% 26.4% 13.8% 20.8% 38.7% 28.9% Bush (election) Weather Forecasting Combined (bag of words) Bag of words news Market History Parsed news Combined (parsing) Parsing the sentences disambiguates word relationships such as what it is that grew, and who defeated whom.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Reading the Markets: Forecasting Public Opinion of Political Candidates by News Analysis

Media reporting shapes public opinion which can in turn influence events, particularly in political elections, in which candidates both respond to and shape public perception of their campaigns. We use computational linguistics to automatically predict the impact of news on public perception of political candidates. Our system uses daily newspaper articles to predict shifts in public opinion as...

متن کامل

Stock Price Forecasting with Support Vector Machines Based on Web Financial Information Sentiment Analysis

The stock price forecasting has always been considered as a difficult problem in time series prediction. Mass of financial Internet information play an important role in the financial markets, information sentiment is an important indicator reflecting the ideas and emotions of investors and traders. Most of the existing research use the stock's historical price and technical indicators to predi...

متن کامل

Presenting a model for Multiple-step-ahead-Forecasting of volatility and Conditional Value at Risk in fossil energy markets

Fossil energy markets have always been known as strategic and important markets. They have a significant impact on the macro economy and financial markets of the world. The nature of these markets are accompanied by sudden shocks and volatility in the prices. Therefore, they must be controlled and forecasted by using appropriate tools. This paper adopts the Generalized Auto Regressive Condition...

متن کامل

Prediction Markets versus Alternative Methods. Empirical Tests of Accuracy and Acceptability

he success of prediction markets in the field of election forecasting made them increasingly appealing to organizations and a number of companies started to experiment with them. However, despite widespread initial interest and years of experimental use, there are no major organizations known to use prediction markets as an integral part of their forecasting activities. Prediction markets have ...

متن کامل

Prediction Markets: Fundamentals, Key Design Elements, and Applications

Over the last couple of years, interest in prediction markets as a forecasting method has continuously increased in the scientific world and in industry. Markets provide incentives for information revelation and can be used as a mechanism for aggregating information. So far, prediction markets have done well in every known comparison with other forecasting methods. Whereas information aggregati...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2007