Table of Contents

Preface		xi
Chapter 1	Introduction	1
	1.1 This book and the ancillary material	3
	1.2 Types of machine learning models	4
	1.3 Validation and testing	6
	1.4 Data cleaning	14
	1.5 Bayes’ theorem	16
	Summary	19
	Short concept questions	20
	Exercises	21
Chapter 2	Unsupervised Learning	23
	2.1 Feature scaling	24
	2.2 The k-means algorithm	25
	2.3 Choosing k	28
	2.4 The curse of dimensionality	31
	2.5 Country risk	31
	2.6 Alternative clustering algorithms	35
	2.7 Principal components analysis	39
	Summary	43
	Short concept questions	44
	Exercises	45
Chapter 3	Supervised Learning: Linear and Logistic Regression	47
	3.1 Linear regression: one feature	48
	3.2 Linear regression: multiple features	49
	3.3 Categorical features	52
	3.4 Regularization	53
	3.5 Ridge regression	54
	3.6 Lasso regression	58
	3.7 Elastic Net regression	60
	3.8 Results for house price data	62
	3.9 Logistic regression	66
	3.10 Decision criteria	69
	3.11 Application to credit decisions	70
	3.12 The k-nearest neighbor algorithm	76
	Summary	76
	Short concept questions	77
	Exercises	78
Chapter 4	Supervised Learning: Decision Trees	81
	4.1 Nature of decision trees	82
	4.2 Information gain measures	83
	4.3 Application to credit decisions	85
	4.4 The naïve Bayes classifier	91
	4.5 Continuous target variables	95
	4.6 Ensemble learning	98
	Summary	100
	Short concept questions	101
	Exercises	101
Chapter 5	Supervised Learning: SVMs	103
	5.1 Linear SVM classification	103
	5.2 Modification for soft margin	109
	5.3 Non-linear separation	112
	5.4 Predicting a continuous variable	114
	Summary	118
	Short concept questions	118
	Exercises	119
Chapter 6	Supervised Learning: Neural Networks	121
	6.1 Single layer ANNs	121
	6.2 Multi-layer ANNs	125
	6.3 Gradient descent algorithm	126
	6.4 Variations on the basic method	131
	6.5 The stopping rule	133
	6.6 The Black−Scholes−Merton formula	133
	6.7 Extensions	137
	6.8 Autoencoders	138
	6.9 Convolutional neural networks	140
	6.10 Recurrent neural networks	142
	Summary	143
	Short concept questions	144
	Exercises	144
Chapter 7	Reinforcement Learning	147
	7.1 The multi-armed bandit problem	148
	7.2 Changing environment	152
	7.3 The game of Nim	154
	7.4 Temporal difference learning	157
	7.5 Deep Q-learning	159
	7.6 Applications	159
	Summary	161
	Short concept questions	162
	Exercises	163
Chapter 8	Natural Language Processing	165
	8.1 Sources of data	168
	8.2 Pre-processing	169
	8.3 Bag of words model	170
	8.4 Application of naïve Bayes classifier	172
	8.5 Application of other algorithms	176
	8.6 Information retrieval	177
	8.7 Other NLP applications	178
	Summary	180
	Short concept questions	181
	Exercises	181
Chapter 9	Model Interpretability	183
	9.1 Linear regression	185
	9.2 Logistic regression	189
	9.3 Black-box models	192
	9.4 Shapley values	193
	9.5 LIME	196
	Summary	196
	Short concept questions	197
	Exercises	198
Chapter 10	Applications in Finance	199
	10.1 Derivatives	199
	10.2 Delta	202
	10.3 Volatility surfaces	203
	10.4 Understanding volatility surface movements	204
	10.5 Using reinforcement learning for hedging	208
	10.6 Extensions	210
	10.7 Other finance applications	212
	Summary	213
	Short concept questions	214
	Exercises	214
Chapter 11	Issues for Society	217
	11.1 Data privacy	218
	11.2 Biases	209
	11.3 Ethics	220
	11.4 Transparency	221
	11.5 Adversarial machine learning	221
	11.6 Legal issues	222
	11.7 Man vs. machine	223
Answers to End of Chapter Questions			225
Glossary of Terms			243
Index			253