COMP6212 Computational Finance

Index

This is an index for the COMP6212 Computational Finance slides (year 2020/21). Its purpose is to help you find relevant slides for a certain keyword or topic faster. Instead of looking through all the slides manually, simply search this document to quickly find the correct slide set and slide number, which is written like:

        Slide Set Name

• Keyword/topic: slide number

Feel free to correct any mistakes or add any improvements.

Currency

C1 Currency Introduction

• Currency - what it is, what we use it for: 4
• Pre currency

• Exchanging goods for services: 5
• Currency instead of exchanging: 6

• Commodity currency

• Middle way between exchange and today’s currencies: 7
• Downside: Only means of exchange, no standard of value: 8
• Historic uses: 9

• Coins

• First coins: 10
• Given out by the government, more value than material is worth: 11
• Controlled release into the market: 12

• Paper money

• First paper money: 13
• Dustrust in Europe until 1700s: 14

• Backed vs non-backed money

• Gold backed currencies: 15
• Fiat money - not backed by anything: 16

• Hyperinflation in Zimbabwe: 17, 18
• Non-physical money - Western union, credit card: 20
• Exchange rate - different currencies: 21

• Control - supply/demand, inflation: 22
• Foreign exchange market: 23
• Benefits of forex: 24

• Comparison fiat money, crypto, gold

• Cryptocurrency vs fiat currency: 26
• Gold vs fiat vs crypto: 27

C2 Intro Crypto

• Ledgers

• Backbone of economy - traditional centralised ledger, history: 3
• Distributed ledgers technology (DLT)

• Introduction, decentralised network, cryptographically secured: 4
• Usage, classes of distributed ledgers: 5
• Corda DLT: 6
• Advantages: 7

• Downsides of current centralised system: 6

• Blockchain

• A layer on top of the internet: 8
• Series of encrypted blocks with hash values: 9
• Transfer money with public-key cryptography, wallet: 10
• Consensus - why do we need it: 11

• Digital currencies

• History: 16, 17
• Definition, regulated vs unregulated: 13
• Virtual currencies: 13

• Cryptocurrencies

• Crypto is parth of virtual currency, what it uses cryptography for: 15

• Avoiding central authorities, consensus: 18

• How transactions are recorded on the distributed ledger: 19
• How transactions are verified / can be trusted, confirmation, validator: 20
• The six conditions for a cryptocurrency system: 21, 22
• Properties - cryptographic security: 23

• Transactional properties: 24
• Monetary properties: 25

• Advantage - cross border transitions: 28
• Concerns - anonymity used for criminal activity: 29

• Theft and fraud: 30

• Regulations worldwide - by country: 31

• How traditional markets work: 27
• Cryptocurrency Example

• Issue of double spending: 32
• Introduction of blockchain: 33

• Details of a block: 34
• Validity of a translation - adding cryptography: 35
• Immutability of coins: 36
• Removing the central owner: 37

C3 Blocks, Nodes and Forks

• Blockchain

• Cerity, Track, Set rules, Use it - no middleman: 4
• Definition: 5
• Size: 11
• Structure: 12

• Ledgers: centralised vs. decentralised

• Centralised ledgers - definition, drawbacks: 8
• Decentralised

• Definition: 9
• Public vs. private blockchain, permissioned/permissionless: 10

• Bitcoin vs. Etherium: 13
• Node types

• Overview / diagram: 14
• Full nodes, lightweight nodes: 15
• Archival nodes, pruned nodes: 16
• Master nodes: 17
• Mining nodes: 18
• Staking nodes: 19
• Authority nodes: 20

• Consensus - hard fork vs. soft fork:

• Hard fork: 21
• Soft fork: 22
• Why they happen - upgrading or changing: 23

C4 Tokens, and Consensus

• What is money: 2
• Tokens

• What is a token: 3
• Features - digital, programmable, asset-backed: 4
• Tokens are not coins - they are on top of coins: 5
• How do tokens work

• The cycle of tokens: 6
• Example: 7

• Legal situation: 8

• Digital Tokens

• Currency of decentralised applications (Dapps), how to obtain them, programmable: 9
• Types - intrinsic, application, asset-backed: 10
• Issuing tokens:

• Types of issuers: 11
• ICO process of Dapp: 12

• Tokens on a classical network vs. on blockchain network: 13
• Examples: 14

• Consensus

• Three properties: security, fault tolerance, real-time value: 15
• Rules / requirements: 16, 17
• Protocols

• Overview - applications: 18
• Proof of work: 19
• Proof of stake: 20
• Proof of work vs. Proof of stake: 21
• Delegated proof of stake: 22
• Proof of burn, proof of authority: 23
• Byzantine Fault Tolerance, Practical Byzantine Fault Tolerance, Federated Byzantine Agreement: 24
• Raft: 25

C5 Platforms

• Private vs. public blockchain: 3
• Etherium

• Overview: 3
• Smart contracts: 5
• DApps - distributed apps: 6
• Gas - specifying computing power for transactions: 7

• Hyperledger Fabric

• Overview: 8, 9
• Chaincode - smart contracts: 10
• Archival nodes types: 11
• Consensus: 12

• R3’s Corda

• Overview: 14
• CorDapp - smart contracts: 15
• Consensus: 16

• Comparison table Etherium vs. Hyperledger Fabric vs. R3 Corda: 17
• Bitcoin

• Overview: 19
• Transaction: 20
• Consensus: 21

• Ripple

• Overview: 22
• MoneyGram partnering: 23
• Main usage - central currency for cross-border transactions: 24, 28
• Consensus: 25, 26
• Comparison with Bitcoin: 27
• Comparison with Ethereum: 28

• Comparison table Bitcoin vs. Ripple: 29
• Issues of Crypto

• Scalability: 30
• Consensus, built-in cryptocurrency: 31

C6 Smart Contracts

• A special account controlled by code: 3
• Application in ethereum: 4
• Example scenario - payment of employees

• Introduction: 5
• Contract PayThem code: 6, 7, 8, 9, 10, 11
• Deployment: 12

• Design

• Minimal design - only put necessary things on the blockchain: 14, 15
• What to define in a smart contract: 16
• Example of when to not use a smart contract: 17
• What the smart contract should ensure: 18
• Simplicity means clarity and avoiding defects: 19

• Plan for failure

• Why bugs are an issue: 20
• How to avoid bugs or other problems: 21
• General strategies to avoid failure

• Check time / whether contract is still active: 22
• Emergency stop - by admins: 23, 24
• Rate limiters: 25
• Delay actions: 26, 27
• Limit the balance: 28

• UX problems

• Inconsistent UX for different crypto currencies: 30
• Users require knowledge of crypto currency: 31
• Poor payment network - scalability issues: 32
• Lack of regulations - advantage and problem at the same time: 33
• Why UX design is important: 34, 35

C7 Micropayments

• Moving money internationally - with distributed ledgers:8
• Bitcoin

• Advantages recap: 10, 11
• Bitcoin as an alternative platform: 12

• Micropayments Overview - definition: 13
• Application

• Vending machines: 14
• Artists, writers, charities, tipping: 15
• Still small solutions / early day: 16
• Crypto for micropayments in the future: 17

• Rise of crypto

• Financial crash - how it helped crypto to become more popular: 19
• Will crypto take over fiat currencies? 20
• Hype around crypto - downsides: 21
• Deflation risk: 22
• Benefits: 23
• Advantages as a medium of exchange: 24

• Cryptocurrency as a commodity?

• Transfers, credit money to commodity money: 25
• Credit relationships, demand for central bank money: 26

• Central banks

• The role of central banks - monetary policy: 27
• Central banks response to crypto: 28

• China

• China banned initial coin offerings (ICOs) - mining in China: 29
• Chinese Renminbi becoming a cryptocurrency: 30
• One day everyone will use China’s digital currency: 31

• Cryptocurrency as a financial instrument - ICO: 32
• Future - stable coin: 33

Finance

F1_1 Introduction to Financial Terms (Part 1)

• Stocks

• Stock market - definition: 3
• Equities - stocks, IPO: 4
• Secondary market - shareholder meetings, dividends: 5

• Bonds

• Definition: 6
• Advantage - steady and reliable income: 7
• Risk free, basic rate: 8

• Commodities

• Definition - future contracts: 9
• Usage - budgeting, volatile market, risky: 10

• Derivatives

• Definition - underlying assets: 11
• Futures

• Definition - insurance: 12
• Risks: 13

• Swaps

• Definition - exchange cash flows or liabilities: 14
• Risks: 15

• Options

• Definition - time sensitive: 16
• Example: 17
• Call options: 18
• Put options: 19
• Advantages: 20
• Disadvantages: 21

• Stock valuation - absolute vs. relative: 22
• Market index

• Definition: 23
• Stock market index - example: 24
• Example for Asian index: 25

• Market cap (capitalization)

• Large market cap

• Definition: 26
• Characteristics: 27

• Small market cap, mid market cap: 28

• Mutual funds: 29, 30, 36
• Investing

• Definition: 32
• Value investing: 33
• Minimum investment, goals and risk: 34
• Brokers charging commission - there’s no free lunch: 35
• Diversify and reduce risks: 37

F1_2 Introduction to Finance 2

• Efficient market

• Definition - stock prices reflect information: 3
• Hypothesis - stocks always trading for fair value: 4
• Why it is not always true: 5

• Arbitrage

• Definition - price differences in markets: 6
• Example: 7
• How you can benefit: 8

• Bull and Bear

• Bullish markets - optimistic about stock rise: 9
• Bearish markets - pessimistic about a stock or market: 10

• Hedging

• Definition - reducing risk, trade-off: 11
• Practices: 12
• Diversification: 13
• Trade-offs: 14
• Spread Hedging: 15
• Risks: 16

• Forward contracts

• Definition - buy in the future for predetermined price: 17
• Contract may gain or lose value: 18
• Calculating return

• Expected stock price: 19
• Expected return: 20
• Expected return including carry costs: 21
• Expected return including dividends: 22
• Example: 23

• Shorts

• Definition - speculation that stock will go down: 24
• What can go wrong - risks: 25

• Fundamental analysis

• Definition - measuring the stock’s intrinsic value: 26
• Quantitative and qualitative data: 27
• Random walk

• Definition - past data cannot be used for prediction: 28, 31
• Example - goat in a field: 29
• Relating the example back to finance: 30
• Criticism: 32

• Technical analysis: 33
• Fundamental vs. technical analysis: 34

F2_1 Introduction to Portfolios (Part 1)

• Time horizon & risk

• Returns, standard deviation: 3
• Downside risk, risky stock: 4
• Time horizon - long vs. short: 5

• Present value of money

• Motivation: 6
• Definition of net present value: 7
• Example - money deposit in bank: 8
• Comparing investments with net present value: 9

• Utility

• Definition - assign numbers to alternatives: 10
• Total utility - definition and example: 11
• Marginal utility

• Definition: 12
• Explanation with graph: 13

• Total vs. marginal utility: 14
• Economic utility - determines the price: 15
• Expected utility

• Hypothesis: 16
• Expected return: 17

• Utility function and indifference curve

• The utility function plotted as indifference curve: 18
• Example: 19
• Definition of indifference curve: 20

• Types of investors

• Definition - risk neutral, risk averse, risk seeking: 21
• Utility and investments - formula: 22
• Expected return vs standard deviation: 23

• Portfolio

• Definition: 24
• Approach - diversification: 25
• Investment portfolio goals: 26
• Portfolio analysis: 27
• Portfolio return: 28

F2_2 Introduction to Portfolios (Part 2)

• The portfolio optimization problem: 3
• Variance

• Definition, formula: 4
• Total variance - systematic risk and non-systematic risk: 5

• Correlation and Covariance

• Definition - what they have in common: 6
• Covariance

• Definition: 7
• Formulas for two stocks: 8
• Example with two stocks: 9

• Correlation

• Definition: 10
• Formula linking covariance and correlation: 11
• Formula: 12

• Expected return and variance

• Formulas for two asset portfolio: 13
• Example: 14, 15
• Relationship between return and variance

• What does it mean: 16
• Assumptions: 17

• Portfolio risk

• Definition: 18
• Two assets example

• Variance, covariance: 19
• Weight, portfolio return, correlation: 20
• How correlation impacts risk with different weights: 21
• What a correlation of 1, 0 and -1 means: 22

• More than two assets

• Variance for 3 assets: 23, 24
• Variance for many assets: 25

• Efficient frontier

• Definition - diagram: 26
• Further explanation of diagram: 27
• CAL (capital allocation line)

• Adding risk free assets to portfolios: 28
• Diagram showing CAL lines added: 29
• Definition: 30
• Bond vs. portfolio risk: 31
• Lending vs. borrowing: 32

• Optimal Investor Portfolio

• Risk vs return - indifference curves: 33
• Combining indifference curves with efficient frontier: 34, 35

• Capital Market Line (CML)

• Definition: 36
• What the CML shows: 37
• Example of CML and formulas: 38
• Tangency portfolio - most efficient portfolio: 39

F2_3 Introduction to Portfolios (Part 3)

• Single factor model

• Definition - formula: 4
• Security return vs market return plot: 5

• Capital Asset Pricing Model (CAPM)

• Definition - relationship between systematic risk and expected returns: 6
• Risk measure beta: 7, 11
• Assumptions: 8
• Example: 9
• Calculate the price of a risky asset - formula: 10
• Example company expected returns: 12
• Caveats / downsides: 13

• CAPM Applications

• Sharpe Ratio

• Definition - formula: 16
• How to use it - measure performance of portfolio: 17

• Treynor Ratio

• Definition - formula: 18
• Only uses historical data: 19

• M-Squared - Definition, formula: 20
• Jensen’s Alpha

• Definition - formula: 21
• Interpretation: 22

• Sortino Ratio - Definition, formula: 23, 24

• Distribution of Risk

• Gaussian distribution

• Definition: 27
• Probability density function: 28
• Example: 29

• Standard normal distribution

• Definition: 28
• Normal distribution of a portfolio: 29, 30

• Multivariate Gaussian Distribution

• Motivation, definition: 32
• Example plots: 33, 34
• Linear transformation of multivariate Gaussian: 35

• Optimise a Portfolio

• Portfolio return as a linear transform: 37
• Putting stock data into matrix - calculating mean price: 39
• Calculating covariance: 40
• Calculating standard deviation: 41
• What weighting is being used? 42
• Summary - calculating the expected return and variance: 43
• Optimization through adapting the weights

• Example plot: 44
• Monti Carlo Simulation: 45
• Recap Monti Carlo: 46, 47

• Constrained optimization: 48
• Estimating parameters: 49, 50
• Transaction costs: 51

F3_1 Stock Price Prediction 1

• Options

• Recap - put and call: 3
• What’s the point of options? 4
• Call option

• Example: 5
• Call pay off diagram 6

• Put option

• Example: 7, 9
• Put pay off diagram: 8

• Put call parity - relationship between put and call

• Definition: 10
• Formulas, example: 11, 12

• Binomial Lattice

• The lattice model - definition: 14
• Assumptions: 15, 16
• Price calculation

• Calculating up and down prices: 18
• Example: 19

• Probability calculation - example: 20
• Calculating a call option (1 year): 21, 22
• Multiple periods

• Example lattice: 23
• Definition: 24
• Price year 2: 25
• Price year 3: 26
• Probability year 2: 27
• Probability year 3: 28
• Calculating the price - backwards: 29 - 34

• Less rigour: 35
• Recap of lattice based model: 37, 38

F3_2 Stock Price Prediction 2

• Ito’s Lemma

• Ito’s process - definition, stochastic, non-stochastic: 4
• Formula: 5
• Examples

• Basic example: 6
• Example forward price: 7, 8
• Example lognormal process: 9, 10

• Wiener process: 11

• Black Scholes

• Combination of bond and stock: 13
• Incorporating wiener process: 14
• Calculating the call option at a specific time: 15
• The Black Scholes PDE (Partial Differential Equation): 16
• Boundary conditions for call options: 17, 18
• Assumption: 19
• Put call parity: 20
• Example Put Option price: 21, 22, 23
• How to find d1 and d2: 24
• Options and dividends: 25
• Volatility

• Definition: 26
• Finding volatility: 27
• Secant numerical method: 28
• Algorithm: 29

• Greek letters

• Overview: 30
• Delta - sensitivity of the stock: 31
• Gamma - sensitivity of the delta: 32
• Vega - sensitivity to the volatility: 33
• Theta - sensitivity in time: 34
• Rho - sensitivity to interest rates: 35
• Greek letters and Black Scholes model: 38

• Relationships: 36, 37

F3_3 Stock Price Prediction 3

• Trends

• Definition - time series: 3
• Discrete-time stochastic process: 4
• Seasonal variation, serial dependence: 5

• Simple technical moving averages (smoothing)

• Definition - formula: 6
• Application, when buy/sell: 7
• Example with plot: 8

• Trend lines: 9
• Momentum indicators - speed at which price changes: 10
• Exponential Moving Average (EMA)

• Definition - formula: 11
• Usage / application: 12
• Example: 13

• Curve fitting

• Definition - fitting a line to a series of data points: 14
• Linear regression

• Definition - relationship between two variables: 16
• Formula: 17
• How to fit the line - least squares approach: 18
• Assumptions: 19
• Goodness of fit: 20

• Polynomial trending: 21
• Other curve fitting - logarithmic, power, exponential: 22

• Statistical analysis of time series

• Application of models in price forecasting: 24
• Autoregressive (AR)

• Application - good for noisy systems: 25
• Formula: 26
• Finding the order of the AR term: 27

• Autocorrelation and Partial Autocorrelation

• Predict the monthly cost of a product: 28
• Formula: 29
• Correlogram: 39
• White noise: 31
• Sessions: 32

• MA (Moving Average)

• What MA models capture: 33
• Formula: 34

• Stationary

• Definition: 35
• Examples: 36

• ARMA (combination of AR and MA)

• Definition: 37, 41, 42
• Example: 38
• Example using Lag Operator: 39
• Lag Operator - Backshift operator: 40
• Formulas: 43, 44

Machine Learning

F4_1_1 Overview of Machine Learning (Part 1)

• What is machine learning? 3
• Supervised vs unsupervised learning

• Definition: 4
• Supervised - visualisation, examples: 5
• Unsupervised - visualisation, examples: 6

• Issues / Challenges

• Data issues, algorithmic issues: 7
• Underfitting, overfitting: 8

• Types of Data

• Nominal data - labels: 10
• Ordinal data - ordering is important: 11
• Interval data - numeric scales: 12
• Ratio data: 13

• Supervised learning

• Classification vs Prediction

• Definition, application: 15
• Training and testing: 16

• From the data to the model: 17
• Prediction/classification of unseen data: 18
• Testing and validation

• Measuring generalisation power, k-fold cross validation: 20
• Using training and testing data: 21
• Percentage split of available data into training, testing, validation: 22
• Cross validation, stratified cross validation: 23, 26
• Example: 24, 25
• Time series cross validation: 27

• Classifiers

• Simple classifiers

• ZeroR, OneR: 29
• Example: 30
• Accuracy of ZeroR used as a baseline - examples: 31

• Decision trees

• Definition: 32
• Building a decision tree - building and pruning phase: 33

• Naive Bayes

• Definition: 34
• Example: 35, 36

• Linear classification: 37
• Support Vector Machine

• Definition - caveats: 38
• Usage / application: 39
• Linear separable data as a requirement: 40
• Defining the margin: 41
• How to deal with nonlinear separable data: 42
• Kernels: 43

• Performance Metrics

• Why accuracy sucks as a sole performance metric: 44
• Confusion matrix: 45
• F1 score: 46, 47
• Precision/recall trade-off: 48

F4_1_2 Overview of Machine Learning (Part 2)

• Linear Regression

• Definition: 5
• Equation format: 6
• How the model is created - example data: 7
• The aim is to minimise the error: 8
• Limitations: 9

• SVM Regression

• Definition: 10
• Equation, visualisation: 11, 12
• Introduction of slack variables, definition of minimization problem: 13, 14
• Using a kernel to enable linear separation: 15

• Polynomial Regression

• Example plot: 16
• Underfitting: 17
• Overfitting: 18
• How to determine the degree? 19
• Performance measures - RMSE, MAE: 20, 21

• Artificial Neural Network

• Definition: 22
• Multilayer Perceptron (MLP): 23, 24, 25

• Association Rule (Unsupervised Learning)

• Definition: 27
• Rule measures - support and confidence: 28
• Association rule mining task, algorithm: 29
• Usage with Weka: 30, 31

• Clustering (Unsupervised Learning)

• Definition: 33
• Objectives, distances, example plot: 34
• Algorithms: 35
• K-Means - iterative distance-based clustering: 36, 37
• Evaluation

• Different clusterer modes: 38
• Classes-to-cluster evaluation: 39

• Other unsupervised learning in finance - factor analysis: 40

F4_1_3 Overview of Machine Learning (Part 3)

• Activation functions (in Neural Networks)

• Definition - linear, non-linear: 3
• Sigmoid or Logistic Activation Function: 4
• Tanh or hyperbolic tangent Activation Function: 5
• Example results - Sigmoid Based Neural Network: 6
• Vanishing Gradient Problem

• Definition: 7
• Why this problem occurs: 8

• ReLU

• Definition - reason why we use it: 10
• Example: 11

• Maxout: 12
• Leaky ReLU: 13

• Training neural networks

• Single layer perceptron - gradient descent: 14
• Choices to make for training - window size, hidden layers, epochs: 15
• Mitigation against slow training: 16

• Fitting

• Overfitting in linear regression: 17
• Underfitting vs overfitting: 18
• Ridge regression for a better fit: 19
• Overfitting

• Lasso: 20
• Avoiding overfitting

• Overview: 21
• Using regularization: 24
• Using drop out: 25 - 32

• Regularization: 22, 23

• Filters

• Kalman Filter

• Definition, usage - filtering out noise from data: 34
• Visualisation: 35
• Formulas - prediction, correction steps: 36, 37, 38

• Extended Kalman Filters (EKF): 39
• Particle Filters - monte carlo technique: 40

F5_1 ML Stock Prediction (Part 1)

• Model and Algorithms

• Overview - ML in finance: 3
• Model - simplified description of a system: 4
• Algorithms - process that uses mathematics techniques: 5

• Advantages of ML in finance: 6
• Application of ML in finance: 7
• Automatic Trading

• Motivation: 8
• Impact - most transactions automated: 9
• Advantages - humans are emotional: 10
• Back testing - investigate wrong results: 11
• Training - sliding windows: 12
• Efficiency: 13
• High Frequency Trading (HFT): 14
• Disadvantages: 15, 16

• Time Series data

• Usage in ML, definition, components: 18
• Trend, Cycle: 19
• Seasonality: 20
• Irregularity: 21
• Analysis

• Charts - example: 22
• Technical and fundamental analysis, patterns: 23
• Definition of terms - opening price, high and low prices, closing price, volume, adjusted closed prices: 24

• Stock index

• Definition: 25
• Example: 26

• Data sets: 30, 31

F5_2 ML Stock Prediction (Part 2)

• Decision Trees

• Overview

• Binary tree structure: 3
• Inputs and output: 4
• Splitting the tree by feature, Gini score: 5

• Regularization to improve generalisation: 6
• Instability - sensitivity to the data: 7
• Application / usage: 8

• Ensemble Learning

• Definition - combination of multiple classifiers: 10
• Requirements to classifiers and training data: 11
• Tips to improve performance: 12
• Random Forest: 13
• Advantages - bagging and pasting: 14
• Stacking: 15

• Neural Networks

• Why they are useful, training through backpropagation: 17
• Multilayer Perceptrons (MLPs)

• Overview: 18
• Disadvantages: 19

• Radial Basis Function (RBF) Networks

• Definition: 20
• Activation function, output, advantages: 21
• Formula, visualisation: 22
• Common radial basis functions: 23, 24
• Structure: 25, 26
• How a RBF classifies: 27

• Recurrent Neural Networks (RNN)

• Overview: 29
• Feeding back the output into the input: 30
• Unfolding RNNs: 31
• Usage for stock price prediction: 32
• Long Short-Term Memory (LSTM)

• Definition - memory cells: 33
• Visualisation - gates: 34, 35, 36
• Four main elements - memory cell and three logistic gates: 37
• Memory cell replaces the “traditional” neurons in hidden layer: 38

• Convolutional Neural Networks (CNN): 39

F5_3 ML Stock Prediction (Part 3)

• Machine Learning (ML) vs. Statistical Models (SM)

• Differences: 3, 4
• Comparisons of predictive performance: 5
• SMs favouring additivity: 6
• When a statistical model is a better choice: 7, 8
• When machine learning is a better choice: 9, 10
• Hybrid Models

• Definition: 11
• Example: 12 - 21

• Dimensionality Reduction

• Definition: 23
• Visual representation - possible positions in different dimensions: 24
• Dimension reduction with projection: 25
• What is dimensional reduction: 26
• Supervised: Linear Discriminant Analysis (LDA)

• Definition: 28
• Primary aim, visualisation: 29

• Unsupervised: Principal Component Analysis (PCA)

• Definition: 30, 31
• How it works: 32
• Right number of dimensions, incremental PCA: 33
• Importance of normalisation / standardisation of data: 34
• Calculation of the PCA components: 35, 36, 37
• Example: 38
• Kernel PCA: 39
• RBF Kernel PCA: 40

F5_4 ML Stock Prediction (Part 4)

• Endogenous Variable

• Definition: 3
• Why they are important: 4
• Properties: 5
• Example: 6

• Exogenous Variable

• Definition: 7
• Properties: 8
• Extensions of work by Hutchinson et al.

• Introduction: 9
• Additional features added: 10
• Visualisation: 11
• Data used: 12
• How exogenous variables are used: 13
• How exogenous variables influenced the model: 14

• Sentiment Analysis

• The role of sentiment in decision making - heuristics, framing, market inefficiencies: 16
• Prizes: 17
• Analysis of media streams: 18
• How it is used in finance: 19
• Overview of steps

• Visualisation: 20
• Polarity Detection, Natural Language Processing (NLP): 21
• Simple NLP: 22, 23
• Analysis of the article: 24

• Sentiment analysis for the stock market

• How this benefits you: 25
• Emotion in the stock market: 26
• Market Sentiment

• What it is: 27
• VIX Index, CBOE Volatility Index, Put Call Ratio: 28
• Safe haven assets, risk on / risk off trade: 29
• High-Low index, stock price breadth: 30
• Indicators on CNN website: 31