100% tevredenheidsgarantie Direct beschikbaar na betaling Zowel online als in PDF Je zit nergens aan vast
logo-home
Samenvatting Financial Services Analytics (FSAN) €10,99   In winkelwagen

Samenvatting

Samenvatting Financial Services Analytics (FSAN)

2 beoordelingen
 574 keer bekeken  14 keer verkocht

Samenvatting van de slides en lessen FSAN van Kris Boudt. Bij gebrek aan een cursus heb ik zelf deze gemaakt. Alles staat er in, alsook de 'R Studio scripts' zoals gezien in de slides.

Voorbeeld 10 van de 91  pagina's

  • 31 december 2020
  • 91
  • 2020/2021
  • Samenvatting
Alle documenten voor dit vak (8)

2  beoordelingen

review-writer-avatar

Door: hwugentluc • 3 jaar geleden

NÓG beknopter dan slides...

reply-writer-avatar

Door: jdw99 • 3 jaar geleden

Normaal gezien staat alles vanuit de slides in de samenvatting. 91blz is al tamelijk uitgebreid (voor een samenvatting), niet?

review-writer-avatar

Door: jelled14 • 3 jaar geleden

avatar-seller
jdw99
FSAN 2020-2021
PART 1: TECHNIQUES TO ANALYZE DATA
1. INTRODUCTION TO THE COURSE
1.1. What is FSAN
1.2. FSAN due to changes
 Changes in customer behavior
 Changes in technology
 Changes in profitability
 Changes in competition
1.3. Hurdles in transformation
 Costs
 People
 Technology
 Vision
1.4. Belgian banks
 Phygital approach
 Data-driven
 Digital-first
 Data-driven & AI
1.5. Transform business problem into a data solution
 Business problem
 Data problem
 Data solution
 Business solution
1.6. Introduction to R Studio
2. FROM DATA TO INSIGHT USING FUNCTIONS
2.1. Today’s challenge
 Analytics that transform the data to actionable insights (data science pipeline)
 Engineering
 Preparation
 Analytics
 Functions
 R packages
2.2. Example: from clickstream data to marketing decisions
 Server log
 Transformations from clicks to time spent
2.3. Example: from prices to trend following investment decisions
 Central paradigm of finance
 Risk ON/OFF decision
 Trend following by Mebane Faber
2.4. Example: from prices to return volatility
 Returns & volatility
 Returns
 Return volatility
2.5. Optimization functions
 Optimizations
 Maximizations
 Minimizations
 Equivalence
 Choice of solver
1

, FSAN 2020-2021
3. UNSUPERVISED & SUPERVISED LEARNING
3.1. Machine learning
 Examples of machine learning
 Machine learning & prediction
 Overfitting
 Solution: split the data
 What is a good model?
 Which features to use?
3.2. Supervised learning
 Definitions
 Garbage in, garbage out
 Split in training set & test set
 Choosing the model
 Training the model
 Inspecting the coefficients
 Prediction accuracy
 Cross-validation
3.3. Unsupervised learning
 Definitions
 K-means clustering
 1 feature
 2 features
 Application to detecting macroeconomic regimes

4. ANALYZING HIGH-DIMENSIONAL DATA
4.1. Abundance of data
 Data today
 Analyze data
4.2. Screening the investment universe
 Who is outperforming?
 Conclusions
 Estimates: differences because of luck
 How many unique comparisons can we do?
 Focus on testing underperformance compared to the best one
 Compare to naïve benchmark portfolio
4.3. Regression analysis with many predictors – two step approach using PCA
 Recall the linear model
 Illustration on house price predictions
 Solutions to reduce number of features
 Transformation
 Variable selection
 Steps in principal component analysis (PCA)
4.4. Regression analysis with many predictors – regression analysis with feature selection
 Feature selection
 1st approach: k-variance regression
 2nd approach: feature selection across models with different size




2

, FSAN 2020-2021
5. DATA CLEANING
5.1. Data cleaning
 Importance of data cleaning
 Data cleaning tasks
5.2. Duplicated data
 Causes
 Data entry & human errors
 Join or merge errors
 Bugs & design errors
 Functions for duplicates in R
5.3. Missing data
 What is it?
 How to handle?
 Remove (naïve approach)
 Replace (imputation)
 Functions in R to handle with missing data
 Visualizing
 Naïve approach
 Imputation
5.4. Outliers
 Outliers
 Outlier detection
 Univariate model
 Multivariate model
 Multivariate regression model
 1st approach: univariate approach to outlier detection
 3 sigma rule
 Outlier masking
 Robust estimators
 2nd approach: multivariate mean/covariance approach to outlier detection
 Mahalanobis distance
 3rd approach: multivariate regression approach to outlier detection
 Vertical outliers
 Bad leverage points
 Good leverage points
 Take home message




3

, FSAN 2020-2021
6. ANALYZING TEXTUAL DATA
6.1. Textual data
 Past VS present
 Journey to become machine readable format
 Digitization & digitalization
6.2. Use cases of textual data analysis
 Case 1 – chatbots
 Case 2 – reputation monitoring
 Case 3- investing based on media sentiment
 Case 4 – early warnings in credit risk
 Case 5 – monitoring the macroeconomy
6.3. Content topic analysis
 Learning outcomes
 Vocabulary
 Corpus
 Document
 Tokens
 Word sequences
→ Unigram
→ Bigram
→ Trigram
 Tokenization
 Analysis
 Removing stop words after tokenization of text
 Document feature matrix
 How many tokens are there?
 Dimension reduction
 Illustration
 Word cloud
 Heterogeneity
 Homogeneity
 Example of topic analysis: ECB
6.4. Sentiment analysis
 What is sentiment?
 American association of individual investment sentiment survey
 Issues with survey data
 Estimated sentiment differs from true sentiment
 Release lag
 No ‘travel back in time’ possibility
 Solutions
 Realtime analysis of text
 Lexicon approach to textual sentiment analysis
 Example
 Alternative calculations
 Aggregation




4

, FSAN 2020-2021
PART 1: CASE STUDIES OF FSAN
7. ROBO-ADVISORY IN PORTFOLIO MANAGEMENT
7.1. Steps in personal financial advice that are automated in robo-advisory
 Robo-advisory
 WealthTech
 FinTech
 Pipeline of personal finance advise
 Gather customer data
 Gather financial data
 Integrated asset allocation process
 Chose the securities
 Ensure the follow-up
 Automation of step 1 – gather customer data
 Automation of step 2-4 – profile-portfolio matching
 Automation of step 5 – portfolio rebalancing
7.2. Recent trends
 Growing popularity of ETFs
 Bottom-up approach
 Growing popularity of robo-advisors
7.3. Why does robo-advisors exist?
 Reason 1 – behavioral finance
 Reason 2 – wealth distribution & market segmentation
 Reason 3 – availability of technology
 Reason 4 – advances in behavioral psychology & investing
7.4. Illustration of portfolio optimization with ETFs
 Recap
 Modern portfolio theory of Harry Markowitz
7.5. Conclusion
 Conclusion about investment algorithm
 Comparison of robo-advisors
 Conclusion




5

, FSAN 2020-2021
8. DIGITAL TRANSFORMATION IN LOAN AND INSURANCE DECISIONS
8.1. Recall
 Motives for digitalization in financial services
8.2. Digitalization and the bank-insurance business model
 Bank-insurance is dominant
 Digitalization strategy
8.3. Data-driven decisions in loan decisions
 General problem
 Difficulties
→ PD: probability of default
→ EAD: exposure at default
→ LGD: loss given default
→ EL: expected loss
 Steps to take
→ Collect the data
→ Model specification
→ Train & evaluate model
 Analytics to predict probability of default
8.4. Data-driven decision rules in insurance
 General problem
 Analytics to estimate the fair premium for car insurance
8.5. Conclusion
 Bank-insurance ecosystem is changing




6

, FSAN 2020-2021
9. ELECTRONIC PAYMENTS, BLOCKCHAIN, DIGITAL CURRENCIES
9.1. Introduction
 Shift in payment execution
 Centralized hedger
 Decentralized hedger (disturbed)
 Risk of payment fraud
 Data solution
9.2. Fraud detection methods in payments
 Fraud detection
 Fraud detection algorithms
 Authentication method
 Something you own
 Something you know
 Something you are
 Recency variable in fraud detection
 Fraud detection based on outliers
 Best fraud detection technique
 Confusion matrix
 Implementation of the fraud detecting rules
 What is now the best system?
 Naïve example
9.3. Secure authentication methods
 Online security
 Solutions
 Illustration of hashing
 Consequence of hashing
 Hashing & encryption
 Public key
 Private key
 Creating keys in R
 Illustration
 We need a ledger to avoid double-spending
 Add data to the blockchain
 Mining
9.4. Bitcoin value analysis
 Bitcoins
 Value of BTC
 Return analysis
 Implications for investors seeking for a stable store of values
9.5. Implications for (central) banks
 Implication for banks
 Losses
→ Direct revenue loss
→ Indirect revenue loss
 Solutions
→ Broaden distribution
→ Platformication
 Implications for central banks
 Conclusion
7

, FSAN 2020-2021
PART 3: LIMITS TO DATA-DRIVEN DECISION-MAKING
10. LIMITS TO DATA-DRIVEN DECISION-MAKING
10.1. Data-driven decision-making
 In a digital society, many decisions are automated
 Limits to data-driven decision-making in finance
 Customers
 Profitability
 Ethics
 Accuracy
 Resiliency of the system
10.2. Digital literacy and financial literacy
 Robot-recommended decisions lead to increased importance of individual decision making
 Attention for this in the media
10.3. Digitalization improves profitability? It depends
 Economies of scale
 Consequences
 The winner takes it all
10.4. Data-driven decision making is not so objective as it may seem
 Accurateness is smarter
 Illusion of objective
 Issue of opaqueness
 Issue of non-ethical decisions
 Data bias & discrimination
 Solution: avoid it
10.5. Specific cases of model risk
 Case 1: data-driven decision-making may fail in a changing world
 Case 2: model fails when scaling
10.6. Market impact: increase herding
 Machine learning programs are often constructed on similar lines
 Stop losses
 Good outcomes
 Bad outcomes
 Ugly outcomes
 Feedback loops
10.7. Concern from financial institutions regulator
 Artificial intelligence is reshaping finance
 Diversification
 Regulation
 Dutch central bank imposes SAFEST principles
 Soundness
 Accountability
 Fairness
 Ethics
 Skills
 Transparency
10.8. Conclusion



8

, FSAN 2020-2021

FSAN – Kris Boudt


PART 1:

TECHNIQUES
TO ANALYZE
DATA
9

, FSAN 2020-2021
LECTURE 1 – INTRODUCTION TO THE COURSE
 WHAT IS FSAN?
 Analytics: systematical analysis of data with the business objective of growing the business, improving
decisions, optimizing the costs or managing the risks.
 Financial services: the sector which contains the following activities:
 Banking (handling deposits and money lending)
 Insurance (pay a premium to be protected against financial losses due to random events)
 Payment services
 Wealth & asset management (investment advisory)
 Consultancy

 WHY FSAN? DUE TO CHANGES!
 Changes in consumer behavior
 More demanding in terms of user experience
 Simple purchasing process
 Quick response
 Required personalization
 Required low costs
 Embraced digitalization
 High trust in information technology (IT) firms
 Interact with an increasing number of digital devices (PC, laptop, smartphone, tablet, smartwatch…)
 Accept that user data is used for corporate purposes
 Accept to interact with robots (chatbots, automated investment advice…)
 Changes in technology
 More communications on digital devices
 More data is stored and processed
 More decisions can be data-driven (evidence based) & even automated
 Changes in profitability for banks
 The profitability for banks is under pressure
 ROE is declining year after year due to the overcapacity & the low margins
 Solutions are mergers & digitalization
 Aiming for state-of-the-art technology
 Stay relevant (grow the business, what do consumers really want?)
 Be efficient (reduce operating costs)
 Success in digitalization (more revenues & less costs to create more profits)
 Changes in competition
 While traditional banks operate in payments, lending, deposits… the new entrants in the market have
specialized themselves in one specific service (Apple Pay, Google Pay, Rabobank…)

Incumbent institutions Other finetech firms
KBC, BNP Paribas Fortis, Deutsche Bank... Armor, Transpay, Wirecard, Kickpay, C2FO...


INVESTORS CUSTOMERS

Technology providers & ICT companies
New digital-based institutions
(incl. BigTech frims)
N26, Ion Bank, Hello Bank, Bunq...
Amazon, Google, Apple, Facebook, Microsoft...



10

Voordelen van het kopen van samenvattingen bij Stuvia op een rij:

√  	Verzekerd van kwaliteit door reviews

√ Verzekerd van kwaliteit door reviews

Stuvia-klanten hebben meer dan 700.000 samenvattingen beoordeeld. Zo weet je zeker dat je de beste documenten koopt!

Snel en makkelijk kopen

Snel en makkelijk kopen

Je betaalt supersnel en eenmalig met iDeal, Bancontact of creditcard voor de samenvatting. Zonder lidmaatschap.

Focus op de essentie

Focus op de essentie

Samenvattingen worden geschreven voor en door anderen. Daarom zijn de samenvattingen altijd betrouwbaar en actueel. Zo kom je snel tot de kern!

Veelgestelde vragen

Wat krijg ik als ik dit document koop?

Je krijgt een PDF, die direct beschikbaar is na je aankoop. Het gekochte document is altijd, overal en oneindig toegankelijk via je profiel.

Tevredenheidsgarantie: hoe werkt dat?

Onze tevredenheidsgarantie zorgt ervoor dat je altijd een studiedocument vindt dat goed bij je past. Je vult een formulier in en onze klantenservice regelt de rest.

Van wie koop ik deze samenvatting?

Stuvia is een marktplaats, je koop dit document dus niet van ons, maar van verkoper jdw99. Stuvia faciliteert de betaling aan de verkoper.

Zit ik meteen vast aan een abonnement?

Nee, je koopt alleen deze samenvatting voor €10,99. Je zit daarna nergens aan vast.

Is Stuvia te vertrouwen?

4,6 sterren op Google & Trustpilot (+1000 reviews)

Afgelopen 30 dagen zijn er 71498 samenvattingen verkocht

Opgericht in 2010, al 14 jaar dé plek om samenvattingen te kopen

Start met verkopen
€10,99  14x  verkocht
  • (2)
  Kopen