Upload
cataldo-musto
View
427
Download
2
Tags:
Embed Size (px)
DESCRIPTION
Smart Companies and Artificial Intelligence - AI*IA (Associazione Italiana Intelligenza Artificiale) event. Florence. May 14, 2013.
Citation preview
Recommender Systems di prodotti bancari-finanziari
Giovanni Semeraro , Cataldo Musto
Smart Companies and Artificial IntelligenceFirenze (Italy) - May 14, 2013
outline
• Background
• Needs Allocation
• Anima SGR’s Progettometro
• From Needs to Asset Allocation: recommender systems
• State of the art: Collaborative filtering, content-based filtering
• Our choice: case-based reasoning
• A possible use case
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
Background
ObjectWay Finance-as-a-ServiceSmart Application Software & Services for Financial
Services Operators
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
Background
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
Background
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
BackgroundWealth Management reference framework
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
Current work
• Progettometro
• iPad app (https://itunes.apple.com/it/app/progettometro/id515222798?mt=8)
• iOs 4.3 required
• Designed by Anima SGR
• Helps people building their life projects
• Tool for needs allocation
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
Progettometroprofile selection
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
Progettometrofive stereotypes
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
Progettometroinput information
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
Progettometroprojection
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
Progettometrolife projects
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
Progettometroinformation about life projects
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
Progettometroupdated projection
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
Progettometrofinal report
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
from needsto asset allocation
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
researchquestion
is it possible to evolve a needs allocation tool
towards an asset allocation one by exploiting artificial
inteligence techniques?
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
our proposal: personalization
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
to introduce an holistic vision of the user
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
to adapt asset portfolios on the ground of personal user profile and needs
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
to introduce a tool helpful for supporting financial advisors (not for private investors!)
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
SolutionRecommender Systems
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
Recommender Systems
Relevant items (movies, news, books, etc.) are suggested to the user according to her preferences.
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
definitionRecommender Systems have the goal of guiding the
users in a personalized way to interesting
or useful objects in a large space of possible options.
Burke, 2002 (*)(*) Robin D. Burke: Hybrid Recommender Systems: Survey and Experiments. UMUAI, volume 12, issue 4, 331-370 (2002)
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
does it fit our scenario?“we are leaving the age of information, we are entering the age of recommendation”
(C.Anderson, The Long Tail. Wired. October 2004)
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
Amazon.com
Testo
“ The technology is used by shopping websites such as Amazon, which receives about 35 percent of its revenue via product recommendations. It is also used by coupon sites like Groupon; by travel sites to suggest flights, hotels, and rental cars; by social-networking sites such as LinkedIn; by video sites like Netflix to recommend movies and TV shows, and by music, news, and food sites to suggest songs, news stories, and restaurants, respectively. Even financial-services firms recently began using recommender systems to provide alerts for investors about key market events in which they might be interested” (N.Leavitt, “A technology that comes highly recommended” - http://tinyurl.com/d5y5hyl)
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
Netflix.com
Recommendations
“ The technology is used by shopping websites such as Amazon, which receives about 35 percent of its revenue via product recommendations. It is also used by coupon sites like Groupon; by travel sites to suggest flights, hotels, and rental cars; by social-networking sites such as LinkedIn; by video sites like Netflix to recommend movies and TV shows, and by music, news, and food sites to suggest songs, news stories, and restaurants, respectively. Even financial-services firms recently began using recommender systems to provide alerts for investors about key market events in which they might be interested” (N.Leavitt, “A technology that comes highly recommended” - http://tinyurl.com/d5y5hyl)
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
Recommender Systemscurrent literature
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
Recommender Systemscurrent literature
Collaborative/Social FilteringContent-based Filtering
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
Recommender Systemscurrent literature
Collaborative/Social FilteringContent-based Filtering
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
collaborative recommendersSuggest items that similar users liked in the past.
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
collaborative recommendersSuggest items that similar users liked in the past.
It capitalizes the ‘word of mouth’ effect
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
collaborative recommendersexample: user-item matrix
item 1 item 2 item 3 item 4
user1 ♥ ♥
user2 ♥ ♥ ♥
user3 ♥
user4
♥ ♥
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
collaborative recommenderstarget user: user 4
item 1 item 2 item 3 item 4
user1 ♥ ♥
user2 ♥ ♥ ♥
user3
♥
user4
♥ ♥
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
collaborative recommenderslooking for like-minded users
item 1 item 2 item 3 item 4
user1
♥ ♥
user2 ♥ ♥ ♥
user3 ♥
user4
♥ ♥
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
collaborative recommendersrecommendationsitem 1 item 2 item 3 item 4
user1
♥ ♥
user2 ♥ ♥ ♥
user3 ♥
user4
♥ ♥
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
Recommender Systemscurrent literature
Collaborative/Social FilteringContent-based Filtering
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
content-based recommendersSuggest items similar to those liked in the past by the user
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
content-based recommenderskey concepts
•Each item has to be described through a set of textual features
•Movie plots, content of news, book summaries, etc.
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
content-based recommendersexample: news recommendations
Items
♥
♥
User Profile
User is interested in news articles
about sports, football,
cycling, etc.
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
content-based recommendersexample: news recommendations
Items
♥
♥
Recommendations
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
content-based recommendersexample: news recommendations
Items
♥
♥
Recommendations
XG.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
content-based recommendersexample: news recommendations
Items
♥
♥
Recommendations
XG.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013.
both collaborative and content-based filtering
are not feasible for recommending financial products.
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
CF drawback: flocking
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
CF drawback: flocking
Similar users receive similar assets.
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
CF drawback: flocking
Too many users could be moved towards the same suggestions
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
CF drawback: flocking
consequence: price manipulation (as in trader forums)
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
CBRS drawback: poor content
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
CBRS drawback: poor content
Features describing both assets and private investors are very
poor (e.g. risk profile)
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
CBRS drawback: poor content
Difficult to calculate the overlap between item and user (feature) description
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
Solution
Knowledge-based Recommender Systems
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
Knowledge-based Recommender Systems• Useful for complex domains
• Computers, cameras, financial products
• Need a deep understanding of the domain
• Typically encoded by experts
• Focused on producing correct recommendations
• Focused on explanations of the recommendations
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
Knowledge-based Recommender Systems• Recommendation process
• Gets information about user needs;
• Exploits the knowledge stored in the KB to meet user needs;
• (eventually) ask user to relax or to modify some of the needs (e.g. expected interest rate);
• Proposes a recommendation.
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
we focus on a subclass of
knowledge-based recommender systems
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
we focus on a subclass of
knowledge-based recommender systems
case-based recommender systems
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
case-based RSs• Knowledge base Case base
• Similar problems solved in the past are used as knowledge base
• To each case is assigned a set of features
• User needs
• Description of the case
• The recommendation process consists of the retrieval and the adaptation of similar already solved cases
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
case-based RSssolving cycle
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
case-based RSsformally
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
case-based RSsformally
item model
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
case-based RSsformally
item model
= (model, producer, megapixel, zoom, etc.)
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
case-based RSsformally
item model
= (product, asset class, macro asset class, yield, etc.)
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
case-based RSsformally
item model
user model
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
case-based RSsformally
item model
user model
= (risk profile, experience, goals, etc.)
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
case-based RSsformally
item model
user model
session model
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
case-based RSsformally
item model
user model
session modelevaluation
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
case-based RSsformally
item model
user model
session modelevaluation
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
case-based RSsformally
item model
user model
session modelevaluation
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
$ 174.18http://tinyurl.com/d3nt2fq
given a case base, it is necessary to
define similarity metrics to compute how similar two cases are
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
case-based RSssimilarity
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
case-based RSssimilarity
state of the art:heterogeneous euclidean overlap metric
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
case-based RSssimilarity
n features
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
case-based RSssimilarity
weight of the i-th feature
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
case-based RSssimilarity
distance
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
the retrieved solutions can be refined and modified before being
proposed to the user
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
solutions considered as ‘correct’ can be stored in the case base and
exploited again in the future
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
case-based reasoning for financial product recommendation
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
scenario
“Scrooge McDuck wants to get richer. He decided to invest some of his savings and he asked for help to a
financial advisor”
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
step 1user modeling
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
scenario
Which features may describe
Scrooge McDuck?
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
scenario
User FeaturesRisk Profile
Financial ExperienceFinancial SituationInvestment GoalsTemporal Goals
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
scenario
User FeaturesRisk Profile: Low
Financial Experience: HighFinancial Situation: Very HighInvestment Goals: MediumTemporal Goals: Medium
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
scenario
User FeaturesRisk Profile: Low
Financial Experience: HighFinancial Situation: Very HighInvestment Goals: MediumTemporal Goals: Medium
MiFID-based
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
in a classical pipeline, the target user would have received a “model” porfolio tailored on her profile
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
in a pipeline fostered by a recommender system, the financial advisor can analyze the portfolios proposed to
similar users.
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
step 2retrieval of similar users
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
retrieval
case base
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
retrieval0.3
0.7
0.9
0.1
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
retrieval0.3
0.7
0.9
0.1
similarity score
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
retrieval0.3
0.7
0.9
0.1
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
retrieval0.3
0.7
0.9
0.1
helpful cases
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
in real-world scenarios, the case base contains much more helpful cases
usually, it is necessary to introduce some strategy to diversify similar cases
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
case-based RSsdifferentiate solutions
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
to each case is assigned an agreed portoflio the set of the portfolios represents the set of the possible recommendations
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
retrieval
Obbligazionario Euro Bot 30%Obbligazionario High Yield 15%Obbligazionario Globale 15%
Azionario Europa 20%Azionario Paesi Emergenti 12%
Flessibili Bassa Volatilità 8%
Obbligazionario Euro Bot 30%Obbligazionario High Yield 10%Obbligazionario Globale 22%
Azionario Europa 23%Azionario Paesi Emergenti 7%
Flessibili Bassa Volatilità 8%
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
how to combine the retrieved cases?several strategies available
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
step 3revise and review
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
revise and review
Obbligazionario Euro Bot 30%Obbligazionario High Yield 12.5%Obbligazionario Globale 18.5%
Azionario Europa 21.5%Azionario Paesi Emergenti 9.5%
Flessibili Bassa Volatilità 8%
rough average
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
revise and reviewclustering (proposing diversified solutions)
Obbligazionario Euro Bot 30%
Obbligazionario High Yield 15%
Obbligazionario Globale 15%
Azionario Europa 20%
Azionario Paesi Emergenti 12%
Flessibili Bassa Volatilità 8%
Obbligazionario Euro Bot 30%
Obbligazionario High Yield 10%
Obbligazionario Globale 22%
Azionario Europa 23%
Azionario Paesi Emergenti 7%
Flessibili Bassa Volatilità 8%
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
financial advisor and private investor can further discuss the portfolio
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
revise and review
Original Discussed Gap
Obbligazionario Euro Bot 30% 30%
Obbligazionario High Yield 12.5% 10% -2.5%
Obbligazionario Globale 18.5% 20% +1.5%
Azionario Europa 21.5% 24% +2.5%Azionario Paesi
Emergenti 9.5% 8% -1.5%Flessibili Bassa
Volatilità 8% 8%
interactive personalization
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
an evaluation score is finally assigned to the proposed solution
yield, e.g.
retain
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
good solutions are stored in the case base and exploited for future recommendations
retain
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
case base
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
(new) case base
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
recap• Case-based reasoning for recommending financial products
• Goal: to help financial promoters considering solutions proposed to similar users
• Case base: user features and agreed portfolios
• User features: risk profile (MiFID questionnaire), financial experience, financial situation, investment goals, temporal goals
• Portfolio: model portfolio, macro asset classes, asset class distribution, products, etc.
• Similarity: HEOM to retrieve similar ‘cases’
• Revise and Review: several strategies for cases aggregation and combination
• Retain: considering external factors (e.g. yield) to evaluate the effectiveness of the proposed solution
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
open points• Research is not over :-)
• How to model investors?
• How to model portfolios?
• Which features should be assigned a greater weight?
• Which one is the best strategy to aggregate recommended portfolios?
• How to model temporal constraints?
• How to consider contextual information (e.g., stock market situation) ?
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013
questions?
Cataldo Musto, Ph.D [email protected]
prof. Giovanni Semeraro [email protected]
G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013