March 24, 2015
You will find below this short event highlights video the recordings and access to the slides of all sessions
Armando gives an introduction to what is Big Data in Finance, what are its applications, and describes the Big Data Analytics market.
Traditional macroeconomic & geopolitical analysis is often unsatisfactorily dependent on infrequent official data points or subjective assessment of a country or economy.
The availability of more unstructured and unique data sets, and the ability to process and transform them, gives economists the opportunity to interpolate official data with early warnings of unexpected events or empirical evidence of trends that have, until now, not been readily available.
This presentation explores which data sets RGE sees coming to the fore and how might they be used to improve economists' capabilities as well as add more value for clients.
There's no doubt news, or text, analytics is alive and kicking. Financial Institutions may not be shouting about it, but it’s not in their nature to share the secret sauce.
In this presentation, Peter shows what the latest news analytics look like and discusses how some of the top financial firms use them to enhance traditional alpha models. He provides examples of how this data can be used for event trading – understanding what events are typically reversal vs. momentum-driven. In addition, he considers how sentiment can be used as a stand-alone indicator or as a filter on top of traditional alpha signals. Finally, he shows an example of how abnormal news volume can be a valuable input into volatility prediction models.
Using a standard value relevance approach, Jeremiah studies the market price of two aspects of business press coverage: journalists’ commitment to cover a company and the amount of news dissemination a company receives.
He finds a positive market price for journalists’ coverage commitment and a negative price for news dissemination when controlling for the coverage commitment. The coverage commitment also yields market prices that place less weight on accounting information consistent with investors’ use of journalists’ coverage to monitor corporate value.
Quantitative managers have long acknowledged the risk of relying on homogeneous data and tools. The question we now ask is have they changed their behavior?
Chris discusses the challenges that quants continue to face when searching for new datasets and their value in alpha generation. This includes patents, property details for REITs and social media sentiment. He also discusses the challenges of utilising new datasets and conclude with an example for how he has used a combination of unique and traditional datasets to build a sector rotation model.
To Abstract, Slides & Video
“Uncertainty” is one of the most widely used but least quantified terms in the economic lexicon. Until now we have not had dedicated analytic methods to effectively use uncertainty for anticipatory market decisions.
Using the convergence of Predictive Content analytics and Big Data, we can now use the very nature and components of uncertainty to create top-down analytics and better leading indicators of sentiment influences on the financial markets.
In this presentation, Rich describes the composition of today’s environmental influences on economic behavior, consumers to the financial markets, Trendpointers’ macro sentiment analytics methodology, and how his directional market signals can consistently outperform benchmarks such as the S&P.
Juan describes Dow Jones’ methods and approaches towards the automatic discovery of entities in news, and the understanding and modeling of relations or interactions between these entities.
He also describes approaches and methods to large scale parallelization and the visualization or interactive interfaces they have prototyped around this data.
The presentation finishes with a summary of the most important directions of this research and where the most promising applications lie.
Tom discusses the wide variety of data sources the team of data-driven journalists at the Wall Street Journal mine, the software they use in their work and some of the resulting pieces of investigative journalism they produce.
Please use your business email. If you don't have one, please email us at email@example.com.
We will process your personal data with the purpose of managing your personal account on
RavenPack and offering our services. You can exercise your rights of access, rectification,
erasure, restriction of processing, data portability and objection by emailing us at firstname.lastname@example.org. For more information, you can
Your request has been recorded and a team member will be in touch soon.
High inflation has returned in developed markets after decades of lying low. In our latest paper, we show how to build an inflation-based asset allocation strategy using sentiment data and we illustrate that sentiment-based strategies outperform models that depend merely on past observed inflation values.
This year's RavenPack Research Symposium brought two intense days of knowledge sharing in London and New York, from 25 top experts in natural language processing, quantitative investing and machine learning. Together, we explored how firms can leverage new language models to generate alpha, better manage risk and respond to calls for more sustainable investment practices.
Human capital is at the heart of value creation. Our latest research demonstrates how unprecedented workforce insights, sourced from over 200 million job postings, can generate more alpha.