EFMA Customer Week - April 2013 Tomás Pariente Lobo – Atos Spain
description
Transcript of EFMA Customer Week - April 2013 Tomás Pariente Lobo – Atos Spain
EFMA Customer Week - April 2013
Tomás Pariente Lobo – Atos Spain
FIRSTEuropean research for web information extraction
and analysis for supporting financial decision making
Vision
Innovation
Tools
Motivation
Why FIRST? - Motivations
3
The most reliable data sources today…
…also have their weakness!They do not consider unstructured data, rumors, market sentiments, etc.
Why FIRST? - Motivations
4
Example: Apple iPhone 1 Announcement on 2007-01-09
Stock prices were skyrocketing after the announcement. However, the announcement could be sensed before…
Why FIRST? - Motivations
5
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.
Why FIRST? – MotivationsA growing universe of unstructured data
… how to separate the wheat from the chaff ?
6
Vision
Innovation
Tools
Motivation
FIRST 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
European-funded research project
Who is behind FIRST?
Industrial partners
SMEs
Academic/Research
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
FIRST Vision
Structured
UnstructuredBlog, analysis, bulletin boards… Unreliable, poor quality, noisy…
AUTOMATION
Acquisition AnalysisProcessing Decision support
Financial Resources
11
Automated data processing
Overall Goal: Mixing structured information and unstructured web data in specific decision making processes
Four steps in the macro-process of converting data into information are tackled, in our solutions tailored to the financial services market:
Data stream acquisition
Real-time processing
Sentiment building
Decision Support System
Sentiment from web data streams
Sentiment is extracted from data streams and correlated with events
Sentiment in Financial Services?
In Sept 2011, the sentiment turns from a long time of positive values to negative. A big plunge in the price happens shortly after, accompanied by a series of negative events (lost deals etc)
Sentiment cross-over
Sentiment cross-over happens
before price plunge
Vision
Innovation
Tools
Motivation
Mining the Web for financial texts
Data Acquisition pipeline: Web mining
Streaming
Cleaning
Natural Language preprocessing and entity
extraction
Financial terms, Companies,
Intruments …
Data acquisition after one year
Some numbers176 Web sites2,671 RSS sources~40,000 documents per day>10.000.000 documents by end of 2012o And growing
Essential for future evaluation and analysis
17
Analysing sentiments in Web texts
Document with
sentiment sentences
Aggregatedsentiments
SENTIMENTAGGREGATION
per object and feature
The Analytical Pipeline: Identify, extract, classify, aggregate
Documentwithbasic
annotations
SENTIMENTCLASSIFICATION
per object and feature
Sentiment Sentences
ObjectIndicators
Positive sentiment
18
Supporting the decision making process
Qualitative Modeling
Knowledge Base
Outputs:
Forecasts of volatility or returns, Alert on pump and
dump, Reputation change of a counterpart
Signals,Charts,
Topic Spaces,Topic Trends,
Reports…
Machine Learning
Techniques
Visualization Techniques
FIRSTAcquisition &
Analytical Pipelines Forecasting
Models
The Decision Support techniques: Analysis and visualization
19
Glassbox model
Document
sentencesObjectsFeatures
Sentiment
20
Drill down
Sentiment analysis & decision making
The integrated model of FIRST and its innovations
In the following slides we will rapidly check results from incorporating sentiments in retail brokerage, investment management and reputational risk scenarios
Main areas of research
•Sentiment analysis
•DSS models
•Stream visualization
•Scaling strategy
Early adopters
•Slovenian presidential elections
•GAMA Perception Analytics
Vision
Innovation
Tools
Motivation
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.
23
The three usecases in the words of the FIRST UC-Owners
UC#1 – Market Surveillance “The development of surveillance scenarios based on unstructured information will allow the
compliance offices to better investigate on unusual and suspicious trading activities and to better understand trends and patterns” – Stefan Queck, Business Dev. Manager at NEXT.
“Especially in time of financial crises, new regulatory requirements and reputation loss risks, the financial industry is interested in new methods and approaches to detect abuse trading behaviour”– Wolfgang Fabisch, CEO at NEXT.
UC#2 – Reputational Risk Management “From the early prototype release, we are looking forward to utilising in a real-life
environment the FIRST solution” – Maria Costante, Responsible for reputational risk modelling and Pillar 3 at Gruppo Montepaschi.
“We already discussed the tool we are setting up in European contexts, and we are looking forward to presenting the first results, already in 1H/2012” – Giorgio Aprile, Head of Reputational and Operational Risks at Gruppo Montepaschi.
UC#3 – Retail Brokerage “When presenting the usecase to potential customers, they showed interest in this kind of
data and the resulting tools” – Michael Diefenthäler, Director of Product Mgmt at IDMS. “We are looking forward to present the FIRST results to a variety of customers.” – Peter
Heister, Head of Sales EMEA at IDMS.
Reputational risk
Query• on-demand• routinary
Sentiment analysis
IE
Unstructured sources
Risk reporting:•reputational trends for each counterpart• events/topic•data sources drill-downs• …
What-if scenarios:• events• probability-weighted risk scenarios• …
Ontology
Customer an d product data
(internal sources)
PerformanceMismatchingVolumesNr. Customers
Structured sources
….. Need for integrating online unstructured data analysis with the current analysis on financial structured data
Reputation cockpit
Reputational Risk Index (RI)
Model
Application scenarios
Goal: to measure and to report, in quasi-real time, on reputational risk, using internal as well external data sources, to be integrated into a single reputation engine and application scenario
Retail brokerage @ work
Sentiments: Leverage of the investment process by assessment of unstructured information
1. Unburden the actor of reviewing various sources repeatedly by automation of this task
2. Provide different levels of sentiments, e.g. for single instruments and sectors
3. Support individual decision making by incorporating sentiments
Market surveillance @ work
1) Buying
Typically thinly-traded stocksBlog A
Blog B
Blog C
4) Selling
On artificial price level
p
t
2) Disseminating inaccurate
or misleading information
3) Waiting for changesof market price
• Identification and classification of unstructured information
• Quite understandable generation of alerts
• Functionalitites to handle alerts
• Comparison of market, institute specific and unstructured information
Decision support in evaluation of suspicious constellations
Market surveillance @ work
Structured InformationStructured Information
Transactiondata
Employee data
Instrument Reference data
Ad-hoc news
Market data
Order data
Unstructured InformationUnstructured Information
Discussion Forums
„News“
Blogs
Social Networks
Sentiment Analysis
Scenario Analysis
Analytic Models
Visualisation
Sentiment Analysis
Scenario Analysis
Analytic Models
Visualisation
Broadend approach of detecting suspicious trading behaviour
Early recognition of trends and patterns
Decision support in investigation and escalation
Benefits for the market
Real-life implementation @ B-NEXT, Germany.Contact: [email protected]
29Stay tuned (http://project-first.eu/)
AcknowledgementThe 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