How to build AI for the financial sector

1. P E T E R @ S I L O . A I | 1 1 / 2 0 1 7 A R T I F I C I A L I N T E L L I G E N C E A S A S E R V I C E P E T E R S A R LIN HOW TO BUILD AI FOR THE FINANCIAL SECTOR

2. P E T E R @ S I L O . A I | 1 1 / 2 0 1 7 AI changes finance fundamentally It's impacting every business process

3. P E T E R @ S I L O . A I | 1 1 / 2 0 1 7 AI changes finance fundamentally It's impacting every business process MEET THE SHERLOCKS

4. P E T E R @ S I L O . A I | 1 1 / 2 0 1 7 W H A T I S A I ?

5. P E T E R @ S I L O . A I | 1 1 / 2 0 1 7 “ A N Y D E V I C E T H A T P E R C E I V E S I T S E N V I R O N M E N T A N D T A K E S A C T I O N S T H A T M A X I M I Z E I T S C H A N C E O F S U C C E S S A T S O M E G O A L ”

6. P E T E R @ S I L O . A I | 1 1 / 2 0 1 7 “ A N Y D E V I C E T H A T P E R C E I V E S I T S E N V I R O N M E N T A N D T A K E S A C T I O N S T H A T M A X I M I Z E I T S C H A N C E O F S U C C E S S A T S O M E G O A L ” A C T S - S E N S E S - R E A C T S

7. P E T E R @ S I L O . A I | 1 1 / 2 0 1 7P E T E R @ S I L O . A I | 1 1 / 2 0 1 7 AI is oftentimes SensingSensing M A C H I N E L E A R N I N G C O M P U T E R V I S I O N N A T U R A L L A N G U A G E P R O C E S S I N G P E T E R @ S I L O . A I | 1 1 / 2 0 1 7 and most often not ...

8. P E T E R @ S I L O . A I | 1 1 / 2 0 1 7P E T E R @ S I L O . A I | 1 1 / 2 0 1 7 AI MYTH #1 AI ≠ MACHINES > HUMANS P E T E R @ S I L O . A I | 1 1 / 2 0 1 7

9. P E T E R @ S I L O . A I | 1 1 / 2 0 1 7P E T E R @ S I L O . A I | 1 1 / 2 0 1 7 AI MYTH #2 BEST AI ≠ BEST ALGORITHM P E T E R @ S I L O . A I | 1 1 / 2 0 1 7

10. P E T E R @ S I L O . A I | 1 1 / 2 0 1 7P E T E R @ S I L O . A I | 1 1 / 2 0 1 7 AI FACT #1 AI = TD + ML + HITL P E T E R @ S I L O . A I | 1 1 / 2 0 1 7

11. P E T E R @ S I L O . A I | 1 1 / 2 0 1 7P E T E R @ S I L O . A I | 1 1 / 2 0 1 7 AI FACT #2 BEST AI = BIZ > TECH P E T E R @ S I L O . A I | 1 1 / 2 0 1 7

12. P E T E R @ S I L O . A I | 1 1 / 2 0 1 7P E T E R @ S I L O . A I | 1 1 / 2 0 1 7 ML AS A PROCESS FOR AI 1 . B U S I N E S S O B J E C T I V E 2 . D A T A U N D E R S T A N D I N G 3 . D A T A P R E P A R A T I O N 4 . B U I L D M O D E L 5 . E V A L U A T E M O D E L 6 . D E P L O Y M O D E L P E T E R @ S I L O . A I | 1 1 / 2 0 1 7

13. P E T E R @ S I L O . A I | 1 1 / 2 0 1 7P E T E R @ S I L O . A I | 1 1 / 2 0 1 7 D A T A F I N D P A T T E R N S R E C O G N I Z E S P A T T E R N SC O N T A I N S P A T T E R N S T R A I N A L G O R I T H M D E P L O Y M O D E L N E W D A T A A P P L Y M O D E L DECISION SIGNALS H U M A N I N T H E L O O P DATA, THE OIL OF MACHINE LEARNING … B U T A L W A Y S S T A R T F R O M A C O N C R E T E B U S I N E S S N E E D P E T E R @ S I L O . A I | 1 1 / 2 0 1 7

14. P E T E R @ S I L O . A I | 1 1 / 2 0 1 7P E T E R @ S I L O . A I | 1 1 / 2 0 1 7 HOW TO CREATE VALUE WITH AI?

15. P E T E R @ S I L O . A I | 1 1 / 2 0 1 7P E T E R @ S I L O . A I | 1 1 / 2 0 1 7 HOW TO CREATE VALUE WITH AI? 1 . O P T I M I Z E E X I S T I N G D A T A - D R I V E N S T R A T E G I E S

16. P E T E R @ S I L O . A I | 1 1 / 2 0 1 7P E T E R @ S I L O . A I | 1 1 / 2 0 1 7 HOW TO CREATE VALUE WITH AI? 1 . O P T I M I Z E E X I S T I N G D A T A - D R I V E N S T R A T E G I E S 2 . U S E N E W , A L T E R N A T I V E D A T A S O U R C E S

17. P E T E R @ S I L O . A I | 1 1 / 2 0 1 7P E T E R @ S I L O . A I | 1 1 / 2 0 1 7 A I R I S K Q U A N T T O O L F O R M E A S U R I N G F I N A N C I A L R I S K A I A N A L Y S T T O O L T H A T U N D E R S T A N D S N E W S L I K E A H U M A N A N A L Y S T S I L O B R A I N T O O L F O R M L W I T H A H U M A N I N T H E L O O P P E T E R @ S I L O . A I | 1 1 / 2 0 1 7

18. P E T E R @ S I L O . A I | 1 1 / 2 0 1 7P E T E R @ S I L O . A I | 1 1 / 2 0 1 7 A I R I S K Q U A N T T O O L F O R M E A S U R I N G F I N A N C I A L R I S K

19. P E T E R @ S I L O . A I | 1 1 / 2 0 1 7 I N D U S T R Y C O - O P E R A T I O N A C A D E M I C C O - O P E R A T I O N

20. P E T E R @ S I L O . A I | 1 1 / 2 0 1 7P E T E R @ S I L O . A I | 1 1 / 2 0 1 7 Case: Identify vulnerable banks 2-class classification: Vulnerable vs. tranquil Data Historical distress events Hundreds of risk indicators Measures of interconnectedness AI for financial risk

21. P E T E R @ S I L O . A I | 1 1 / 2 0 1 7P E T E R @ S I L O . A I | 1 1 / 2 0 1 7 RAW DATA RISK INDICATORS INDIVIDUAL RISK NODE & SYSTEM RISK M A C H I N E L E A R N I N G T O M E A S U R E I N D I V I D U A L R I S K E X P E R T S B U I L D & M A C H I N E S S E L E C T K E Y I N D I C A T O R S N E T W O R K S L I N K U P I N T E R C O N N E C T E D R I S K TOOL FOR MEASURING FINANCIAL RISK

22. P E T E R @ S I L O . A I | 1 1 / 2 0 1 7P E T E R @ S I L O . A I | 1 1 / 2 0 1 7 ECB BANK ASSESSMENT EXERCISE IN 2014 M O D E L V S 7 0 0 0 M A N - Y E A R S 2 0 M O S T V U L N E R A B L E B A N K S I N 2 0 1 4Q 2

23. P E T E R @ S I L O . A I | 1 1 / 2 0 1 7P E T E R @ S I L O . A I | 1 1 / 2 0 1 7 A I A N A L Y S T T O O L T H A T U N D E R S T A N D S N E W S L I K E A H U M A N A N A L Y S T

24. P E T E R @ S I L O . A I | 1 1 / 2 0 1 7P E T E R @ S I L O . A I | 1 1 / 2 0 1 7 BANK DISTRESS DETECTION IN NEWS 1. CAN WE DETECT EVENTS BASED ON TEXT? 2. CAN WE OBTAIN DESCRIPTIONS OF EVENTS? STEP 1: LEARNING SEMANTIC VECTORS, THROUGH WORD PREDICTION STEP 2: LEARNING TO PREDICT EVENTS, WITH ARTICLES' SEMANTIC VECTORS

25. P E T E R @ S I L O . A I | 1 1 / 2 0 1 7P E T E R @ S I L O . A I | 1 1 / 2 0 1 7 NEWS NEWS FACTS NUMERICAL INDICATORS STOCK IMPACT TOOL THAT UNDERSTANDS NEWS LIKE A HUMAN ANALYST Natural-language processing Detect events & values that represent news facts. Machine learning Build and select relevant numerical indicators. Artificial Intelligence quant Measure stock impact of events – the event delta.

26. P E T E R @ S I L O . A I | 1 1 / 2 0 1 7P E T E R @ S I L O . A I | 1 1 / 2 0 1 7 S I L O B R A I N P L A T F O R M T O O L F O R M L W I T H A H U M A N I N T H E L O O P

27. P E T E R @ S I L O . A I | 1 1 / 2 0 1 7 D A T A I N P U T M O D E L I N G O U T P U T OP E N A I D E P LOY MENT P LAT FORM A P I : S R E P O R T S T O O L K I T S D A S H B O A R D S P E T E R @ S I L O . A I | 1 1 / 2 0 1 7 NLP / Text processing Computer Vision Complex risk modelling Reinforcement learning General ML E X A M P L E S O F S I L O B R A I N M O D U L E S Active learning C L I E N T - S P E C I F I C F O R M A T

28. P E T E R @ S I L O . A I | 1 1 / 2 0 1 7 S O U R C E & S H A R E I N T E L L I G E N C E A N N O T A T E & L A B E L F O R M A C H I N E L E A R N I N G V I S U A L I Z E D A T A & M L O U T P U T F I N A N C I A L I N T E R C O N N E C T E D N E S S C O L L A B O R A T I V E M A C H I N E L E A R N I N G W I T H A H U M A N I N T H E L O O P R I S K I N T E L L I G E N C E C A S E S T U D Y: P E T E R @ S I L O . A I | 1 1 / 2 0 1 7

29. P E T E R @ S I L O . A I | 1 1 / 2 0 1 7P E T E R @ S I L O . A I | 1 1 / 2 0 1 7 AI HOW- TO 3 , 0 7 3 E X E C U T I V E S 1 6 0 C A S E S T U D I E S 1 4 S E C T O R S 1 0 C O U N T R I E S H O W B U S I N E S S E S S U C C E E D W I T H A I H B R ‘ 1 7

30. P E T E R @ S I L O . A I | 1 1 / 2 0 1 7P E T E R @ S I L O . A I | 1 1 / 2 0 1 7 AI HOW- TO 1 . D O N ’ T B E L I E V E T H E H Y P E 2 . B E L I E V E T H E H Y P E 3 . W I T H O U T S U P P O R T F R O M L E A D E R S H I P … 4 . Y O U D O N ’ T H A V E T O G O I T A L O N E O N A I 5 . D O N ’ T P U T T E C H N O L O G Y T E A M S S O L E L Y I N C H A R G E 6 . T A K E A P O R T F O L I O A P P R O A C H 7 . D E E P L E A R N I N G I S N O T R I G H T F O R E V E R Y T H I N G 8 . D I G I T A L C A P A B I L I T I E S C O M E B E F O R E A I 9 . B I G G E S T C H A L L E N G E S A R E P E O P L E & P R O C E S S E S 1 0 . B E B O L D H B R ‘ 1 7

33. P E T E R @ S I L O . A I | 1 1 / 2 0 1 7P E T E R @ S I L O . A I | 1 1 / 2 0 1 7P E T E R @ S I L O . A I | 1 0 / 2 0 1 7 AI HOW- TO 1 . D O N ’ T B E L I E V E T H E H Y P E 2 . B E L I E V E T H E H Y P E 3 . W I T H O U T S U P P O R T F R O M L E A D E R S H I P … 4 . Y O U D O N ’ T H A V E T O G O I T A L O N E O N A I 5 . D O N ’ T P U T T E C H N O L O G Y T E A M S S O L E L Y I N C H A R G E 6 . T A K E A P O R T F O L I O A P P R O A C H 7 . D E E P L E A R N I N G I S N O T R I G H T F O R E V E R Y T H I N G 8 . D I G I T A L C A P A B I L I T I E S C O M E B E F O R E A I 9 . B I G G E S T C H A L L E N G E S A R E P E O P L E & P R O C E S S E S 1 0 . B E B O L D H B R ‘ 1 7

40. P E T E R @ S I L O . A I | 1 1 / 2 0 1 7P E T E R @ S I L O . A I | 1 1 / 2 0 1 7P E T E R @ S I L O . A I | 1 1 / 2 0 1 7 A R T I F I C I A L I N T E L L I G E N C E A S A S E R V I C E THANKS! PETER SARLIN CO-FOUNDER PETER@SILO.AI @PETERSARLIN @SILO_AI

How to build AI for the financial sector

Recommandé

Recommandé

Contenu connexe

Tendances

Tendances (16)

Similaire à How to build AI for the financial sector

Similaire à How to build AI for the financial sector (20)

Plus de Finanssivalvonta

Plus de Finanssivalvonta (20)

Dernier

Dernier (20)

How to build AI for the financial sector