• Corpus ID: 682373

Economic Prediction using Heterogeneous Data Stremas from the World Wide Web

@inproceedings{Levenberg2013EconomicPU,
  title={Economic Prediction using Heterogeneous Data Stremas from the World Wide Web},
  author={Abby D. Levenberg},
  year={2013}
}
Learning to predict financial and economic variables of interest is a hard problem with a large body of literature devoted to it. Of late there has been a significant amount of work on using sources of text from the Web (such as Twitter or Google Trends) to predict financial and economic variables. Much of this work has relied on some form or other of superficial sentiment analysis to represent the text. In this work we present a novel approach to predicting economic variables using multiple… 

Figures and Tables from this paper

Extracting predictive information from heterogeneous data streams using Gaussian Processes
TLDR
This work considers the problem of forecasting financial time series from a wide range of information sources using online Gaussian Processes with Automatic Relevance Determination (ARD) kernels, and shows evidence that ARD kernels produce meaningful feature rankings that help retain salient inputs and reduce input dimensionality.
Forecasting Time Series from heterogeneous Data Streams using Adaptive Automatic Relevance Determination Gaussian Process Regression S id G hoshal
TLDR
This work considers the problem of forecasting time series from a wide range of information sources using online Gaussian Processes with Automatic Relevance Determination (ARD) kernels and shows evidence that ARD kernels produce meaningful feature rankings that help retain salient inputs and reduce input dimensionality.
Modeling Analysts’ Recommendations via Bayesian Machine Learning
TLDR
The authors argue that there are many similarities between the analyst forecasting problem and a very successful application of IBCC in astronomy, a study in which it dominates heuristic alternatives including simple or weighted averages and majority voting.
Modeling Analysts’ Recommendations via Bayesian Machine Learning
We apply state-of-the-art Bayesian machine learning to test whether we can extract valuable information from analysts’ recommendations of stock performance. We use a probabilistic model for
A distributed real-time data prediction framework for large-scale time-series data using stream processing
TLDR
A distributed real-time data prediction framework for large-scale time-series data, which can exactly achieve the requirement of the effective management, prediction efficiency, accuracy, and high concurrency for massive data sources is provided.
Combined Decision Making with Multiple Agents
TLDR
This thesis introduces efficient and scalable Bayesian inference for decision combination, allowing us to fuse the responses of multiple agents in large, real-world problems and account for the agents’ unreliability in a principled manner.

References

SHOWING 1-10 OF 25 REFERENCES
Predicting Financial Markets: Comparing Survey,News, Twitter and Search Engine Data
TLDR
This paper surveys a range of online data sets and sentiment tracking methods and compares their value for financial prediction of market indices such as the Dow Jones Industrial Average, trading volumes, and market volatility, as well as gold prices.
Textual analysis of stock market prediction using breaking financial news: The AZFin text system
TLDR
This research examines a predictive machine learning approach for financial news articles analysis using several different textual representations: bag of words, noun phrases, and named entities and found that a Proper Noun scheme performs better than the de facto standard of Bag of Words in all three metrics.
Text-Driven Forecasting
TLDR
Text-driven forecasting is proposed as a challenge for natural language processing and machine learning to connect real-world measurable phenomena through statistical models.
Text Mining Systems for Market Response to News: A Survey
Several prototypes for predicting the short-term market reaction to news based on text mining techniques have been developed. However, no detailed comparison of the systems and their performances is
Quantifying Trading Behavior in Financial Markets Using Google Trends
TLDR
By analyzing changes in Google query volumes for search terms related to finance, this work finds patterns that may be interpreted as “early warning signs” of stock market moves.
Complex dynamics of our economic life on different scales: insights from search engine query data
TLDR
It is found clear evidence that weekly transaction volumes of S&P 500 companies are correlated with weekly search volume of corresponding company names, and a recently introduced method for quantifying complex correlations in time series finds a clear tendency that search volume time series and transactionvolume time series show recurring patterns.
Predicting the Index of Consumer Sentiment When It Isn ’ t Measured
Cost and space limitations on questionnaires usually restrict opinion surveys to a small number of topics that are high on the public agenda at polling times. The result is very few time trends with
The Econometric Modelling of Financial Time Series.
Text mining approaches for stock market prediction
TLDR
The main components of such forecasting systems have been introduced and the way whereby the main components are implemented compared and the potential future research activities have been suggested.
...
1
2
3
...