Table of Contents
Preface |
|
xiii |
|
|||
|
|
|
|
|||
Chapter 1 |
Introduction |
1 |
|
|||
|
1.1 Machine learning vs. statistics |
4 |
|
|||
|
1.2 This book and the ancillary material |
5 |
|
|||
|
1.3 Types of machine learning models |
6 |
|
|||
|
1.4 Generative AI |
8 |
|
|||
|
1.5 Validation and testing |
10 |
|
|||
|
1.6 Data cleaning |
18 |
|
|||
|
1.7 Bayes theorem |
20 |
|
|||
|
Summary |
22 |
|
|||
|
Short
concept questions |
24 |
|
|||
|
Exercises |
24 |
|
|||
|
|
|
|
|||
Chapter 2 |
Unsupervised Learning |
27 |
|
|||
|
2.1 Feature scaling |
28 |
|
|||
|
2.2 The k-means
algorithm |
29 |
|
|||
|
2.3 Choosing k |
34 |
|
|||
|
2.4 The curse of dimensionality |
37 |
|
|||
|
2.5 Country risk |
38 |
|
|||
|
2.6 Alternative clustering approaches |
43 |
|
|||
|
2.7 Principal components analysis |
45 |
|
|||
|
Summary |
49 |
|
|||
|
Short
concept questions |
50 |
|
|||
|
Exercises |
51 |
|
|||
|
|
|
|
|||
Chapter 3 |
Supervised Learning:
Linear and Logistic Regression
|
53 |
|
|||
|
3.1 Linear regression: one feature |
54 |
|
|||
|
3.2 Linear regression: multiple features |
55 |
|
|||
|
3.3 Categorical features |
58 |
|
|||
|
3.4 Regularization |
60 |
|
|||
|
3.5 Ridge regression |
60 |
|
|||
|
3.6 Lasso regression |
64 |
|
|||
|
3.7 Elastic Net regression |
67 |
|
|||
|
3.8 Application to Predicting House Prices |
68 |
|
|||
|
3.9 Logistic regression |
73 |
|
|||
|
3.10
Decision criteria |
75 |
|
|||
|
3.11
Application to credit decisions |
76 |
|
|||
|
3.12
The k-nearest neighbor algorithm |
83 |
|
|||
|
Summary |
84 |
|
|||
|
Short
concept questions |
85 |
|
|||
|
Exercises |
86 |
|
|||
|
|
|
|
|||
Chapter 4 |
Supervised Learning: Decision Trees |
89 |
|
|||
|
4.1 Nature of decision trees |
90 |
|
|||
|
4.2 Information gain measures |
91 |
|
|||
|
4.3 Application to LendingClub
data |
93 |
|
|||
|
4.4 The nave Bayes classifier |
98 |
|
|||
|
4.5 Continuous target variables |
102 |
|
|||
|
4.6 Ensemble learning |
106 |
|
|||
|
Summary |
107 |
|
|||
|
Short
concept questions |
108 |
|
|||
|
Exercises |
109 |
|
|||
|
|
|
|
|||
Chapter 5 |
Supervised Learning:
SVMs |
111 |
|
|||
|
5.1 Linear SVM classification |
111 |
|
|||
|
5.2 Modification for soft margin |
118 |
|
|||
|
5.3 Non-linear separation |
121 |
|
|||
|
5.4 Predicting a targets value |
123 |
|
|||
|
Summary |
126 |
|
|||
|
Short
concept questions |
127 |
|
|||
|
Exercises |
128 |
|
|||
|
|
|
|
|||
Chapter 6 |
Supervised Learning:
Neural Networks |
129 |
|
|||
|
6.1 ANNs with a single hidden layer |
129 |
|
|||
|
6.2 Multi-layer ANNs |
134 |
|
|||
|
6.3 Other activation functions |
136 |
|
|||
|
6.4 Gradient descent algorithm |
138 |
|
|||
|
6.5 Variations on the basic method |
144 |
|
|||
|
6.6 The stopping rule |
145 |
|
|||
|
6.7 The Black−Scholes−Merton
formula |
147 |
|
|||
|
6.8 Extensions |
150 |
|
|||
|
6.9 Understanding volatility movements |
151 |
|
|||
|
Summary |
156 |
|
|||
|
Short
concept questions |
156 |
|
|||
|
Exercises |
157 |
|
|||
Chapter 7 |
Further
Applications of Neural Networks |
159 |
|
|||
|
7.1 Autoencoders and
PCA |
159 |
|
|||
|
7.2 General autoencoder
design |
162 |
|
|||
|
7.3 Variational autoencoders |
164 |
|
|||
|
7.4 Generative adversarial networks |
166 |
|
|||
|
7.5 Recurrent neural networks |
169 |
|
|||
|
7.6 Convolutional neural networks |
170 |
|
|||
|
Summary |
174 |
|
|||
|
Short concept
questions |
175 |
|
|||
|
Exercises |
176 |
|
|||
|
|
|
|
|||
|
|
|
|
|||
Chapter 8 |
Reinforcement
Learning |
177 |
|
|||
|
8.1 The multi-armed bandit problem |
178 |
|
|||
|
8.2 Changing environment |
183 |
|
|||
|
8.3 The game of Nim |
185 |
|
|||
|
8.4 Temporal difference learning |
188 |
|
|||
|
8.5
When the opponent learns |
191 |
|
|||
|
8.6
Deep Q-learning |
192 |
|
|||
|
8.7 Distributional reinforcement learning |
192 |
|
|||
|
8.8 Playing chess |
193 |
|
|||
|
8.9 Applications |
194 |
|
|||
|
8.10 Optimal trade execution |
196 |
|
|||
|
8.11
Data issues |
198 |
|
|||
|
Summary |
199 |
|
|||
|
Short
concept questions |
200 |
|
|||
|
Exercises |
201 |
|
|||
|
|
|
|
|||
Chapter 9 |
Natural Language
Processing |
203 |
|
|||
|
9.1 NLP Generations |
204 |
|
|||
|
9.2 Generation 1 |
206 |
|
|||
|
9.3 Generation 2 |
208 |
|
|||
|
9.4 Generation 3 |
210 |
|
|||
|
9.5 Generation 4 |
212 |
|
|||
|
Summary |
212 |
|
|||
|
Short
concept questions |
213 |
|
|||
|
Exercises |
214 |
|
|||
Chapter 10 |
Sentiment Analysis |
215 |
|
|||
|
10.1 Pre-processing |
217 |
|
|||
|
10.2 Word Lists |
218 |
|
|||
|
10.3 Naive Bayes classifier |
219 |
|
|||
|
10.4 Application of other algorithms |
223 |
|
|||
|
10.5 Sentiment analysis for stock trading |
224 |
|
|||
|
Summary |
227 |
|
|||
|
Short
concept questions |
227 |
|
|||
|
Exercises |
227 |
|
|||
Chapter 11 |
Large Language Models |
229 |
|
|||
|
11.1 General Concepts of LLMs |
230 |
|
|||
|
11.2 Foundation LLMs and limitations |
232 |
|
|||
|
11.3 Retrieval augmented generation |
235 |
|
|||
|
11.4 Prompt Engineering |
237 |
|
|||
|
11.5 Applications of LLMs |
239 |
|
|||
|
11.6 LLM agentic system |
245 |
|
|||
|
Summary |
246 |
|
|||
|
Short
concept questions |
246 |
|
|||
|
Exercises |
247 |
|
|||
Chapter 12 |
Model Interpretability |
249 |
|
|||
|
12.1 Linear regression |
252 |
|
|||
|
12.2 Logistic regression |
255 |
|
|||
|
12.3 Black-box models |
258 |
|
|||
|
12.4 Local interpretability |
260 |
|
|||
|
12.5 Global Interpretability |
264 |
|
|||
|
Summary |
265 |
|
|||
|
Short
concept questions |
266 |
|
|||
|
Exercises |
267 |
|
|||
|
|
|
|
|||
Chapter 13 |
Issues for Society and AI Regulations |
269 |
|
|||
|
13.1 Data privacy |
270 |
|
|||
|
13.2 Biases |
271 |
|
|||
|
13.3 Ethics |
273 |
|
|||
|
13.4 Transparency |
274 |
|
|||
|
13.5 Adversarial machine learning |
275 |
|
|||
|
13.6 Legal issues |
276 |
|
|||
|
13.7 AI Regulations |
277 |
|
|||
|
13.8 Man vs. machine |
279 |
|
|||
|
|
|
|
|||
Answers to
Short Concept Questions |
|
283 |
||||
Glossary of Terms |
|
305 |
||||
Index |
|
319 |
||||