Case-based Recommender Systems for Personalized Finance Advisory - talk by Cataldo Musto and Giovanni Semeraro - workshop FinRec 2015 - 1st International Workshop on Personalization & Recommender Systems in Financial Services, Graz, Austria, Apr 16th 2015
Workshop Website: http://finrec.ist.tugraz.at
Top 5 Benefits OF Using Muvi Live Paywall For Live Streams
Ā
Case-based Recommender Systems for Personalized Finance Advisory
1. Cataldo Musto, Giovanni Semeraro
Case-based Recommender Systems
for Personalized Finance Advisory
Graz (Austria) - 16.04.2015
2. one minute
on the Web
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
3. C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
4. we can handle 126 bits of information
we deal with 393 bits of information
ratio: more than 3x(Source: Adrian C.Ott,The 24-hour customer)
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
5. (from Matrix)
decision-making
is actually challenging
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
6. paradox of choice
(Barry Schwartz,TED talk āWhy more is lessā)
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
7. (ļ¬nancial) overload
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
8. solution: personalization
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
9. to adapt asset
portfolios
on the ground of personal
user proļ¬le and needs
Insight:
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
10. Solution
Recommender Systems
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
11. Recommender Systems
Relevant items (movies, news, books, etc.) are suggested to
the user according to her preferences.
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
12. deļ¬nition
Recommender 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)
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
13. does it ļ¬t our scenario?
āwe are leaving the age of information, we are entering the age of recommendationā
(C.Anderson,The LongTail.Wired. October 2004)
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
14. Recommender Systems
ā[...] 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 ļ¬ights, hotels, and rental cars; by social-
networking sites such as LinkedIn; by video sites like Netļ¬ix to
recommend movies and TV shows, and by music, news, and food
sites to suggest songs, news stories, and restaurants, respectively.
Even ļ¬nancial-services ļ¬rms recently began using
recommender systems to provide alerts for investors about
key market events in which they might be interestedā
(N.Leavitt,āA technology that comes highly recommendedā - http://tinyurl.com/d5y5hyl)
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
16. Recommender Systems
success stories
āPeople who boughtā¦ā
on Amazon
āDiscoverā
on Spotify
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
17. Recommender SystemsRecommender Systems
unexpected stories
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
18. Recommender SystemsRecommender Systems
unexpected stories
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
19. Recommender SystemsRecommender Systems
unexpected stories
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
20. Recommender SystemsRecommender Systems
unexpected stories
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
21. recommending ļ¬nancial products
is a complex task
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
22. ļ¬ocking
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
23. ļ¬ocking
Too many users could be moved
towards the same suggestions
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
24. ļ¬ocking
consequence: price manipulation
(as in trader forums)
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
25. poor knowledge
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
26. Features describing both assets
classes and private investors are
poorly meaningful
poor knowledge
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
27. poor history
A combination of asset classes
is typically kept for a long time
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
28. Solution
Case-based Recommender Systems
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
29. case-based RSs
ā¢ Inspired by case-based reasoning
ā¢ Similar problems solved in the past are
used as knowledge base
ā¢ Reasoning by analogy
ā¢ The recommendation process relies on
the retrieval and the adaptation of the
solutions adopted to solve similar cases
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
30. ....but
what do we actually mean with ācaseā ?
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
31. case base
ā¢ A case is a the formalization of a
previously solved problem
ā¢ In our setting
ā¢ Description of a user
ā¢ Description of a portfolio
ā¢ An evaluation of the proposed solution
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
32. case-base
example
user solution evaluation
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
33. case-base
example
user solution evaluation
User Features
Risk Proļ¬le: Low
Financial Experience: High
Financial Situation:Very High
Investment Goals: Medium
Temporal Goals: Medium
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
34. case-base
example
user solution evaluation
User Features
Risk Proļ¬le: Low
Financial Experience: High
Financial Situation:Very High
Investment Goals: Medium
Temporal Goals: Medium
Euro Bonds 30%
High-Yield Bonds 10%
Fixed-Rate bonds 22%
Euro Stocks 23%
Emerging Market Stocks 7%
Money Market 8%
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
35. case-base
example
user solution evaluation
User Features
Risk Proļ¬le: Low
Financial Experience: High
Financial Situation:Very High
Investment Goals: Medium
Temporal Goals: Medium
monthly rate (e.g.)
+0.22%
Euro Bond 30%
High-Yield Bonds 10%
Fixed-Rate bonds 22%
Euro Stocks 23%
Emerging Markets Stocks 7%
Money Market 8%
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
36. case-based RSs
solving cycle
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
37. case-based reasoning for
personalized wealth management
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
38. scenario
āScrooge McDuck wants to
get richer. He decided to
invest some of his savings
and he asked for help to a
ļ¬nancial advisorā
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
39. step 1
user modeling
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
40. scenario
Which features
may describe
Scrooge McDuck?
step 1
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
41. scenario
User Features
Risk Proļ¬le: Low
Investment Horizon High
Investment ExperienceVery High
Investment Goals: Medium
Financial Assets: Medium
step 1
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
42. User Features
Risk Proļ¬le: Low
Investment Horizon High
Investment ExperienceVery High
Investment Goals: Medium
Financial Assets: Medium
scenario
MiFID-based
step 1
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
43. scenario
step 1
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
+
Generic Demographical Features
User Features
Risk Proļ¬le: Low
Investment Horizon High
Investment ExperienceVery High
Investment Goals: Medium
Financial Assets: Medium
44. in a classical pipeline, the target user
would have received a āmodelā portfolio
tailored on her proļ¬le
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
45. in a pipeline fostered by a recommender system, the ļ¬nancial
advisor can analyze the portfolios proposed to similar users
to tailor the proposal
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
46. step 2
neighbors identiļ¬cation
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
47. given a case base, it is necessary to
deļ¬ne a similarity measure to
compute how similar two cases are
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
48. neighbors identiļ¬cation
trivial similarity: user match
two cases are similar if they share
exactly the same features
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
49. trivial similarity: user match
two cases are similar if they share
exactly the same features
neighbors identiļ¬cation
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
50. neighbors identiļ¬cation
cases are represented
as points in a vector space
geometrical alternative: cosine similarity
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
51. geometrical representation
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
52. geometrical alternative: cosine similarity
neighbors identiļ¬cation
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
53. case-based RSs
geometrical alternative: cosine similarity
each case is seen as a vector
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
54. case-based RSs
geometrical alternative: cosine similarity
calculation over the n features
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
55. case-based RSs
geometrical alternative: cosine similarity
calculation over the n features
= (risk proļ¬le, experience, goals, etc.)
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
56. case-based RSs
geometrical alternative: cosine similarity
inner product
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
57. case-based RSs
geometrical alternative: cosine similarity
it returns the cosine of the angle
between A and B
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
58. case-based RSs
geometrical alternative: cosine similarity
case_A
case_B
cosine
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
59. scenario
case base
step 2
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
60. scenario
step 2
0.3
0.7
0.9
0.1
similarity score
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
61. scenario
step 2
0.3
0.7
0.9
0.1
neighborhood
(helpful cases)
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
62. step 3
extraction of candidate portfolios
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
63. scenario
Euro Bonds 30%
HighYield Bonds 15%
Fixed Rate Bonds 15%
Europe Stocks 20%
Emerging Markets Stocks 12%
Money Market 8%
Euro Bonds 30%
HighYield Bonds 10%
Fixed Rate Bonds 22%
Europe Stocks 23%
Emerging Markets Stocks 7%
Flessibili BassaVolatilitĆ 8%
step 2
solutions proposed to the neighbors
are labeled as candidate solutions
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
64. step 4
ranking of candidate portfolios
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
65. in real-world scenarios, the case base
contains many helpful cases
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
66. in real-world scenarios, the case base
contains many helpful cases
it is necessary to introduce strategies
to ļ¬lter and rank the cases
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
67. revise
We implemented several ranking strategies
ā¢ Temporal ranking
ā¢ Clustering
ā¢ Diversiļ¬cation
ā¢ Financial Conļ¬denceValue (FCV)
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
68. revise
temporal ranking
solutions are ranked from the newest to the oldest (or viceversa)
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
69. Euro Bonds 30%
HighYield Bonds 15%
Fixed Rate Bonds 15%
Europe Stocks 20%
Emerging Markets Stocks 12%
Money Market 8%
Euro Bonds 30%
HighYield Bonds 10%
Fixed Rate Bonds 22%
Europe Stocks 23%
Emerging Markets Stocks 7%
Money Market 8%
Euro Bonds 15%
HighYield Bonds 25%
Fixed Rate Bonds 10%
Europe Stocks 40%
Emerging Markets Stocks 2%
Money Market 8%
Euro Bonds 20%
HighYield Bonds 20%
Fixed Rate Bonds 12%
Europe Stocks 35%
Emerging Markets Stocks 5%
Money Market 8%
revise
temporal ranking
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
70. Euro Bonds 30%
HighYield Bonds 15%
Fixed Rate Bonds 15%
Europe Stocks 20%
Emerging Markets Stocks 12%
Money Market 8%
olderolder
Euro Bonds 30%
HighYield Bonds 10%
Fixed Rate Bonds 22%
Europe Stocks 23%
Emerging Markets Stocks 7%
Money Market 8%
Euro Bonds 15%
HighYield Bonds 25%
Fixed Rate Bonds 10%
Europe Stocks 40%
Emerging Markets Stocks 2%
Money Market 8%
Euro Bonds 20%
HighYield Bonds 20%
Fixed Rate Bonds 12%
Europe Stocks 35%
Emerging Markets Stocks 5%
Money Market 8%
revise
temporal ranking
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
71. clustering
solutions are clustered and just a small set of centroids is proposed
revise
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
72. clustering
revise
Euro Bonds 30%
HighYield Bonds 15%
Fixed Rate Bonds 15%
Europe Stocks 20%
Emerging Markets Stocks 12%
Money Market 8%
Euro Bonds 30%
HighYield Bonds 10%
Fixed Rate Bonds 22%
Europe Stocks 23%
Emerging Markets Stocks 7%
Money Market 8%
Euro Bonds 15%
HighYield Bonds 25%
Fixed Rate Bonds 10%
Europe Stocks 40%
Emerging Markets Stocks 2%
Money Market 8%
Euro Bonds 20%
HighYield Bonds 20%
Fixed Rate Bonds 12%
Europe Stocks 35%
Emerging Markets Stocks 5%
Money Market 8%
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
73. clusteringcluster 1
revise
Euro Bonds 30%
HighYield Bonds 15%
Fixed Rate Bonds 15%
Europe Stocks 20%
Emerging Markets Stocks 12%
Money Market 8%
Euro Bonds 30%
HighYield Bonds 10%
Fixed Rate Bonds 22%
Europe Stocks 23%
Emerging Markets Stocks 7%
Money Market 8%
Euro Bonds 15%
HighYield Bonds 25%
Fixed Rate Bonds 10%
Europe Stocks 40%
Emerging Markets Stocks 2%
Money Market 8%
Euro Bonds 20%
HighYield Bonds 20%
Fixed Rate Bonds 12%
Europe Stocks 35%
Emerging Markets Stocks 5%
Money Market 8%
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
74. clusteringcluster 1 cluster 2
revise
Euro Bonds 30%
HighYield Bonds 15%
Fixed Rate Bonds 15%
Europe Stocks 20%
Emerging Markets Stocks 12%
Money Market 8%
Euro Bonds 30%
HighYield Bonds 10%
Fixed Rate Bonds 22%
Europe Stocks 23%
Emerging Markets Stocks 7%
Money Market 8%
Euro Bonds 15%
HighYield Bonds 25%
Fixed Rate Bonds 10%
Europe Stocks 40%
Emerging Markets Stocks 2%
Money Market 8%
Euro Bonds 20%
HighYield Bonds 20%
Fixed Rate Bonds 12%
Europe Stocks 35%
Emerging Markets Stocks 5%
Money Market 8%
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
75. insight: ļ¬ltering out too similar solutions
diversiļ¬cation algorithm
revise
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
76. revise
identiļ¬cation of the best subset of similar cases
which maximize the relative diversity
diversiļ¬cation algorithm
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
77. revise
diversiļ¬cation algorithm
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
78. revise
input
similar cases
(candidate solutions)
diversiļ¬cation algorithm
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
79. revise
output
subset of
diversiļ¬ed cases
diversiļ¬cation algorithm
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
80. revise
algorithm
in each step the
portfolio which
best diversiļ¬es
the solutions is
chosen
diversiļ¬cation algorithm
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
81. revise
Solutions with
the highest
quality are
iteratively
chosen
diversiļ¬cation algorithm
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
83. it returns portfolios
that are not so
similar to those
previously put in the
result set
revise
diversiļ¬cation algorithm
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
84. revise
diversiļ¬cation algorithm
Euro Bonds 30%
HighYield Bonds 15%
Fixed Rate Bonds 15%
Europe Stocks 20%
Emerging Markets Stocks 12%
Money Market 8%
Euro Bonds 30%
HighYield Bonds 10%
Fixed Rate Bonds 22%
Europe Stocks 23%
Emerging Markets Stocks 7%
Money Market 8%
Euro Bonds 15%
HighYield Bonds 25%
Fixed Rate Bonds 10%
Europe Stocks 40%
Emerging Markets Stocks 2%
Money Market 8%
Euro Bonds 20%
HighYield Bonds 20%
Fixed Rate Bonds 12%
Europe Stocks 35%
Emerging Markets Stocks 5%
Money Market 8%
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
85. revise
diversiļ¬cation algorithm
Euro Bonds 30%
HighYield Bonds 15%
Fixed Rate Bonds 15%
Europe Stocks 20%
Emerging Markets Stocks 12%
Money Market 8%
Euro Bonds 30%
HighYield Bonds 10%
Fixed Rate Bonds 22%
Europe Stocks 23%
Emerging Markets Stocks 7%
Money Market 8%
Euro Bonds 15%
HighYield Bonds 25%
Fixed Rate Bonds 10%
Europe Stocks 40%
Emerging Markets Stocks 2%
Money Market 8%
Euro Bonds 20%
HighYield Bonds 20%
Fixed Rate Bonds 12%
Europe Stocks 35%
Emerging Markets Stocks 5%
Money Market 8%
X
X
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
86. revise
Financial Conļ¬denceValue (FCV)
ā¢ Simple insight
ā¢ We know the historical yield for each of
the assets class in the portfolio
ā¢ FCV ranks ļ¬rst the solutions composed
by a combination of asset classes close
to the optimal one (according to
previous yield)
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
87. revise
(Generated yield) (Drift Factor)Total yield is the
product of the
yield generated
by each asset
class with the its
percentage in the
portfolio
Ratio between
the yield
generated by the
asset classes in
the portfolio and
its complement
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
Financial Conļ¬denceValue (FCV)
88. revise
Euro Bonds - - - 30%
HighYield Bonds 15%
Fixed Rate Bonds 15%
Europe Stocks +++ 20%
Emerging Markets Stocks 12%
Money Market 8%
Euro Bonds - - - 30%
HighYield Bonds 10%
Fixed Rate Bonds 22%
Europe Stocks +++ 23%
Emerging Markets Stocks 7%
Money Market 8%
Euro Bonds - - - 15%
HighYield Bonds 25%
Fixed Rate Bonds 10%
Europe Stocks +++ 40%
Emerging Markets Stocks 2%
Money Market 8%
Euro Bonds - - - 20%
HighYield Bonds 20%
Fixed Rate Bonds 12%
Europe Stocks +++ 35%
Emerging Markets Stocks 5%
Money Market 8%
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
Financial Conļ¬denceValue (FCV)
89. revise
Euro Bonds - - - 30%
HighYield Bonds 15%
Fixed Rate Bonds 15%
Europe Stocks +++ 20%
Emerging Markets Stocks 12%
Money Market 8%
Euro Bonds - - - 30%
HighYield Bonds 10%
Fixed Rate Bonds 22%
Europe Stocks +++ 23%
Emerging Markets Stocks 7%
Money Market 8%
Euro Bonds - - - 15%
HighYield Bonds 25%
Fixed Rate Bonds 10%
Europe Stocks +++ 40%
Emerging Markets Stocks 2%
Money Market 8%
Euro Bonds - - - 20%
HighYield Bonds 20%
Fixed Rate Bonds 12%
Europe Stocks +++ 35%
Emerging Markets Stocks 5%
Money Market 8%
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
Financial Conļ¬denceValue (FCV)
90. step 5
discussion of the solution
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
91. ļ¬nancial advisor and private investor
can further discuss the portfolio
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
92. review
Original Discussed Gap
Euro Bonds 30% 30%
HighYield Bonds 12.5% 10% -2.5%
Fixed Rate Bonds 18.5% 20% +1.5%
Europe Stocks 21.5% 24% +2.5%
Emerging Markets
Stocks 9.5% 8% -1.5%
Money Market 8% 8%
interactive personalization
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
93. step 6
case base update
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
94. an evaluation score is ļ¬nally assigned to the proposed
solution
yield, e.g.
retain
good solutions are stored in the case base and exploited
for future recommendations
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
95. case base
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
96. (new) case base
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
97. our implementation
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
99. OBWFinance
login screen
advisor-oriented tool
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
100. OBWFinance
client selection
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
101. OBWFinance
recommendation parameters
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
102. OBWFinance
only admins can change the parameters
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
103. OBWFinance
one click to generate recommendations
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
104. OBWFinance
drop-down menu for selecting the best solution
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
105. OBWFinance
assets class
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
106. OBWFinance
yield of the solution
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
107. OBWFinance
chosen portfolio can be further discussed
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
108. evaluation
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
109. evaluation
what is the average yield of
recommended portfolios?
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
110. evaluation
what is the average yield of
recommended portfolios?
can recommender systems suggest
better investment portfolios than
human advisors?
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
111. design of the experiment
ā¢ 1172 users
ā¢ 19 assets classes
ā¢ Different neighborhood sizes
ā¢ Different features describing the users
ā¢ Risk Proļ¬le, Investment Goals, Investment Horizon,
Investment Experience, Financial Assets, Advice Type, Sex,Age
ā¢ Different similarity measures (Cosine vs. UserMatch)
ā¢ Leave-one-out experimental design
evaluation
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
112. experiment 1
user match vs. cosine similarity
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
Yield
0
0,04
0,08
0,12
0,16
0,2
neighbors
1 5 10
0,2
0,19
0,18
0,1
0,11
0,09
User Match Cosine Sim
cosine similarity overcomes user match
113. experiment 2
how many features?
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
Yield
0
0,042
0,084
0,126
0,168
0,21
neighbors
1 5 10
0,2
0,21
0,2 0,2
0,19
0,18
Financial Features Financial + Demographical Features
cosine similarity overcomes user match
114. experiment 3
revise strategies (yield)
best performing conļ¬guration provides 0,28% monthly yield
Yield
0
0,056
0,112
0,168
0,224
0,28
neighbors
1 5 10
0,250,24
0,22
0,270,28
0,22
0,2
0,15
0,13 0,14
0,12
0,09
0,20,210,2
Basic Clustering Diversiļ¬cation FCV FCV + Div
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
115. experiment 3
revise strategies (diversity of the solutions)
ILD=1-average similarity between portfolios
Intra-ListDiversity(ILD)
0
0,14
0,28
0,42
0,56
0,7
neighbors
0,58
0,35
0,7
0,46
0,41
Basic Clustering Diversiļ¬cation FCV FCV + Div
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
116. experiment 4
comparison to baselines (leave-one-out evaluation)
recsys better than humans!
Yield
0
0,056
0,112
0,168
0,224
0,28
neighbors
1 5 10
0,270,28
0,22
0,20,20,2
0,170,170,17
Human Collaborative FCV
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
117. ā¢ FCV calculated on January, 2014
ā¢ Recommendations generated on January, 2014
ā¢ Evaluation of the yield generated from
February 2014 to July 2014
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
experiment 5
ex-post evaluation (6 months, with real data)
118. experiment 5
ex-post evaluation (6 months, with real data)
FCV and Diversiļ¬cation is the best one
Yield
0
0,032
0,064
0,096
0,128
0,16
neighbors
1 5 10
0,060,060,06
0,040,04
0,05
0,11
0,12
0,16
0,09
0,1
0,16
0,06
0,08
0,15
Basic FCV FCV + Div Collaborative Human
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015
119. ā¢Personalized Wealth Management
ā¢ Application of case-based reasoning
ā¢ Geometrical similarity measure to identify the most
similar previously solved cases
ā¢ Introduction of diversiļ¬cation and re-ranking
techniques
ā¢ More than 3% yield for year
ā¢ Experiments shows that recommended portfolios
overcome the real ones for almost all the users
ā¢ Working Demo!
recap
C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory
FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015