Breaking the Kubernetes Kill Chain: Host Path Mount
Personalized Wealth Management through Case-based Recommender Systems
1. AI*IA 2014 - XIII AI*IA Symposium on Artificial Intelligence
Special Track on AI for Society and Economy
Pisa (Italy) - 12.12.2014
Giovanni Semeraro, Cataldo Musto
Personalized Wealth Management
through Case-based
Recommender Systems
2. one minute
on the Web
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
3. G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
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)
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
5. (from Matrix)
decision-making
is actually challenging
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
6. paradox of choice
(Barry Schwartz, TED talk “Why more is less”)
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
7. (financial) overload
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
8. solution: personalization
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
9. Insight:
to adapt asset
portfolios
on the ground of personal
user profile and needs
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
10. Solution
Recommender Systems
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
11. Recommender Systems
Relevant items (movies, news, books, etc.) are suggested to
the user according to her preferences.
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
12. definition
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)
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
13. 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 - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
14. Recommender Systems
“[...] 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 - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
15. Recommender Systems
success stories
“People who bought…”
on Amazon
“Discover”
on Spotify
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
16. Recommender Systems
(unexpected) success stories
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
17. recommending financial products
is a complex task
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
18. flocking
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
19. flocking
Too many users could be moved
towards the same suggestions
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
20. flocking
consequence: price manipulation
(as in trader forums)
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
21. poor knowledge
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
22. poor knowledge
Features describing both assets
classes and private investors are
poorly meaningful
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
23. Solution
Case-based Recommender Systems
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
24. case-based RSs
• Inspired by case-based reasoning
• Similar problems solved in the past are
used as knowledge base
• Reasoning by analogy
• The recommendation process relies on
the retrieval and the adaptation of the
solutions adopted to solve similar cases
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
25. ....but
what do we actually mean with ‘case’ ?
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
26. case base
• A case is a the formalization of a
previously solved problem
• In our setting
• Description of a user
• Description of a portfolio
• An evaluation of the proposed solution
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
27. case-base
example
user solution evaluation
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
28. case-base
example
user solution evaluation
User Features
Risk Profile: Low
Financial Experience: High
Financial Situation: Very High
Investment Goals: Medium
Temporal Goals: Medium
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
29. case-base
example
user solution evaluation
User Features
Risk Profile: Low
Financial Experience: High
Financial Situation: Very High
Investment Goals: Medium
Temporal Goals: Medium
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 - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
30. case-base
example
user solution evaluation
User Features
Risk Profile: Low
Financial Experience: High
Financial Situation: Very High
Investment Goals: Medium
Temporal Goals: Medium
Obbligazionario Euro Bot 30%
Obbligazionario High Yield 10%
Obbligazionario Globale 22%
Azionario Europa 23%
Azionario Paesi Emergenti 7%
Flessibili Bassa Volatilità 8%
monthly rate (e.g.)
+0.22%
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
31. case-based RSs
solving cycle
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
32. case-based reasoning for
personalized wealth management
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
33. 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 - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
34. step 1
user modeling
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
35. scenario
Which features
may describe
Scrooge McDuck?
step 1
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
36. scenario
User Features
Risk Profile: Low
step 1
Financial Experience: High
Financial Situation: Very High
Investment Goals: Medium
Temporal Goals: Medium
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
37. scenario
User Features
Risk Profile: Low
Financial Experience: High
Financial Situation: Very High
Investment Goals: Medium
Temporal Goals: Medium
MiFID-based
step 1
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
38. in a classical pipeline, the target user
would have received a “model” portfolio
tailored on her profile
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
39. in a pipeline fostered by a recommender system, the financial
advisor can analyze the portfolios proposed to similar users
to tailor the proposal
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
40. step 2
retrieval of similar users
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
41. given a case base, it is necessary to
define a similarity measure to
compute how similar two cases are
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
42. given a case base, it is necessary to
define a similarity measure to
compute how similar two cases are
vector space representation
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
43. cosine similarity to get the most similar users
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
44. scenario
step 2
case base
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
45. scenario
step 2
0.3
0.7
0.9
0.1
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
46. scenario
step 2
similarity score
0.3
0.7
0.9
0.1
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
47. scenario
step 2
0.3
0.7
0.9
0.1
neighborhood
(helpful cases)
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
48. scenario
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%
step 2
solutions proposed to the neighbors are labeled as
candidate solutions
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
49. step 3
revise of the solution
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
50. in real-world scenarios, the case base
contains many helpful cases
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
51. in real-world scenarios, the case base
contains many helpful cases
it is necessary to introduce strategies
to filter and rank the cases
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
52. revise
step 3
We defined two ranking strategies
• Diversification
• Financial Confidence Value (FCV)
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
53. revise
diversification
insight: filtering out too similar solutions
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
54. revise
diversification
identification of the best subset of similar cases
which maximize the relative diversity
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
55. revise
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%
diversification
Obbligazionario Euro Bot 15%
Obbligazionario High Yield 25%
Obbligazionario Globale 10%
Azionario Europa 40%
Azionario Paesi Emergenti 2%
Flessibili Bassa Volatilità 8%
Obbligazionario Euro Bot 20%
Obbligazionario High Yield 20%
Obbligazionario Globale 12%
Azionario Europa 35%
Azionario Paesi Emergenti 5%
Flessibili Bassa Volatilità 8%
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
56. revise
Azionario Paesi Emergenti 5%
Flessibili Bassa Volatilità 8% X X diversification
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%
Obbligazionario Euro Bot 15%
Obbligazionario High Yield 25%
Obbligazionario Globale 10%
Azionario Europa 40%
Azionario Paesi Emergenti 2%
Flessibili Bassa Volatilità 8%
Obbligazionario Euro Bot 20%
Obbligazionario High Yield 20%
Obbligazionario Globale 12%
Azionario Europa 35%
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
57. revise
FCV
• Simple insight
• We know the historical yield for each of
the assets class in the portfolio
• FCV ranks first the solutions composed
by a combination of asset classes close
to the optimal one (according to
previous yield)
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
58. revise
FCV
Total yield is the (Generated yield) (Drift Factor)
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
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
59. 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%
revise
Obbligazionario Euro Bot --- 15%
Obbligazionario High Yield 25%
Obbligazionario Globale 10%
Azionario Europa +++ 40%
Azionario Paesi Emergenti 2%
Flessibili Bassa Volatilità 8%
Obbligazionario Euro Bot --- 20%
Obbligazionario High Yield 20%
Obbligazionario Globale 12%
Azionario Europa +++ 35%
Azionario Paesi Emergenti 5%
Flessibili Bassa Volatilità 8%
FCV
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
60. 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%
revise
Obbligazionario Euro Bot --- 15%
Obbligazionario High Yield 25%
Obbligazionario Globale 10%
Azionario Europa +++ 40%
Azionario Paesi Emergenti 2%
Flessibili Bassa Volatilità 8%
Obbligazionario Euro Bot --- 20%
Obbligazionario High Yield 20%
Obbligazionario Globale 12%
Azionario Europa +++ 35%
Azionario Paesi Emergenti 5%
Flessibili Bassa Volatilità 8%
FCV
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
61. step 4
review
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
62. financial advisor and private investor
can further discuss the portfolio
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
63. review
interactive personalization
Original Discussed Gap
Euro Bot 30% 30%
Obbligazionario
High Yield 12.5% 10% -2.5%
Obbligazionario
Globale 18.5% 20% +1.5%
Obbligazionario
Azionario Europa 21.5% 24% +2.5%
Azionario Paesi
Emergenti 9.5% 8% -1.5%
Flessibili Bassa
Volatilità 8% 8%
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
64. step 5
retain
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
65. retain
an evaluation score is finally assigned to the proposed
solution
yield, e.g.
good solutions are stored in the case base and exploited
for future recommendations
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
66. case base
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
67. (new) case base
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
68. evaluation
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
69. evaluation
what is the average yield of
recommended portfolios?
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
70. evaluation
what is the average yield of
recommended portfolios?
can recommender systems suggest
better investment portfolios than
human advisors?
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
71. experiment 1
revise strategies (leave-one-out evaluation)
Yield
0,28
0,224
0,168
0,112
0,056
0
Basic Diversification FCV FCV + Div
0,28 0,27
0,24 0,25
0,22
0,22
0,2
0,15
0,16
0,18 0,18
1 5 10
neighbors
0,13
best performing configuration provides 0,28% monthly yield
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
72. experiment 2
comparison to baselines (leave-one-out evaluation)
Human Collaborative FCV
1 5 10
recsys better than humans!
Yield
0,28
0,224
0,168
0,112
0,056
0
neighbors
0,28 0,27
0,22
0,2 0,2 0,2
0,17 0,17 0,17
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
73. experiment 3
ex-post evaluation (6 months, with real data)
0,16
0,128
0,096
0,064
0,032
Basic FCV FCV + Div Collaborative Human
0,06 0,06 0,06
0,04 0,04
1 5 10
FCV and Diversification is the best one
Yield
0
neighbors
0,05
0,11
0,12
0,16
0,09
0,1
0,16
0,06
0,08
0,15
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14
74. recap
•Personalized Wealth Management
• Application of case-based reasoning
• Geometrical similarity measure to identify the most
similar previously solved cases
• Introduction of diversification and re-ranking
techniques
• More than 3% yield for year
• Experiments shows that recommended portfolios
overcome the real ones for almost all the users
• Working Demo!
G.Semeraro, C.Musto - Personalized Wealth Management through Case-based Recommender Systems
AI*IA 2014 - Special Track on AI for Society and Economy - Pisa (Italy) - 12.12.14