The document discusses the FIRST project, which aims to extract relevant financial information from structured and unstructured data sources to support financial decision making. It notes that current data sources do not consider rumors, market sentiments, etc. The FIRST project vision is to automate the acquisition, processing, analysis and use of financial information from a variety of sources to support near-real time decisions. It outlines the data acquisition, natural language processing, sentiment analysis and decision support pipelines developed by the project. The document also discusses three use cases for the project: market surveillance, reputational risk management, and retail brokerage.
Ensuring Technical Readiness For Copilot in Microsoft 365
European Research for Financial Decision Support
1. FIRST
European research for web information extraction
and analysis for supporting financial decision making
ABI Lab Forum 2012
Tomás Pariente Lobo – Atos Spain
3. Why FIRST? - Motivations
The most reliable data sources today…
…also have their weakness!
They do not consider unstructured data, rumors, market
sentiments, etc.
3
4. Why FIRST? - Motivations
Example: Apple iPhone 1 Announcement on 2007-01-09
Stock prices were skyrocketing after the announcement.
However, the announcement could be sensed before…
4
5. Why FIRST? - Motivations
Example: Market surveillance via FIRST (the Google news case)
September 2008: Google news announced “United Airlines bankruptcy”.
Within 12 minutes stock price decreased 75% wiped out US $ 1bn.
The “news” was actually 6 years old…
Plausibility checking will help in identifying hoaxes: consistence with regulatory news
and other sources.
5
6. Why FIRST? – Motivations
A growing universe of unstructured data
… how to separate the wheat
from the chaff ?
6
8. FIRST Project
European-funded research project
Project facts
Running from October 2010 until
September 2013
9 partners
More than 30 people
Preliminary results available
More to come...
Stay tuned (http://project-first.eu/)
8
9. Who is behind FIRST?
Industrial partners
Academic/Research
SMEs
10. FIRST Vision
Vision
is to make available the relevant information
of the entire financial information space
(including unreliable, unstructured, sentiment sources)
to the decision maker in near-real time
in an automated way
10
13. Mining the Web for financial texts
Data Acquisition pipeline: Web mining
Natural Language
preprocessing and entity
extraction
Streaming
Cleaning
Financial terms,
Companies,
Intruments …
14. Data acquisition after one year
Some numbers
176 Web sites
2,671 RSS sources
~40,000 documents per day
>5,000,000 documents by end of 2011
o And growing
Essential for future evaluation and analysis
14
15. Analysing sentiments in Web texts
The Analytical Pipeline: Identify, extract, classify, aggregate
Document
SENTIMENT Document with SENTIMENT
with Aggregated
CLASSIFICATION sentiment AGGREGATION
basic sentiments
per object and feature sentences per object and feature
annotations
Indicators
Object
Positive sentiment
Sentiment
Sentences
15
16. Supporting the decision making process
The Decision Support techniques: Analysis and visualization
Machine
Learning
FIRST Techniques Outputs:
Acquisition &
Analytical Forecasts of
volatility or returns,
Pipelines Qualitative Forecasting Alert on pump and
Modeling Models dump,
Reputation change
of a counterpart
Signals,
Knowledge Charts,
Base Topic Spaces,
Topic Trends,
Visualization
Reports
Techniques …
16
19. The three FIRST use cases &
their relevance for the industry
Market Surveillance
Capital markets compliance can be automated today using structured data, but
the automation does not take unstructured data into account
FIRST will
make use of large volumes of unstructured data into financial compliance;
develop automated techniques to better detect market abuse/insider
trading..
Reputational Risk Management
No off-the-shelf solutions or methodologies for reputational risk management.
FIRST will
provide a sustainable tool for reputational risk monitoring;
contribute to break new ground in this field of dramatically high impact in FSI.
Retail Brokerage
Today, mainly based on quantitative analysis and key figures.
FIRST will
use unstructured data to leverage both information for private investors and
sophisticated tools for professional users.
19
21. Acknowledgement
The research leading to these results has received funding from the
European Community's Seventh Framework Programme
(FP7/2007-2013) under grant agreement n°257928.
THANKS
Hinweis der Redaktion
Explain the events captured: Greek crisis, sovereing debt crises. EU central bank loans, Italina prime minister change…
Stress and explain (orally) that the analysis is object and feature (eg price, volatility, reputation) specific. Features can be identified by explicit mentions or by indicators that refer to specific features and specific types of objects (eg stocks). The ones in the example are fundamental micro indicators, indicating price change.