book

Machine Learning for Finance

Name: Machine Learning for Finance
ISBN: 9781789136364

by James Le, Jannes Klaas

May 2019

Intermediate to advanced

456 pages

11h 38m

English

Packt Publishing

Read now

Unlock full access

Machine Learning for Finance
Table of Contents
Machine Learning for Finance
Why subscribe?
Packt.com
Contributors
About the author
About the reviewer
Preface
Who this book is for
What this book covers
To get the most out of this book
Download the example code filesDownload the color imagesConventions used
Get in touch
Reviews

1. Neural Networks and Gradient-Based Optimization
Our journey in this book
What is machine learning?
Supervised learning
Unsupervised learning
Reinforcement learning
The unreasonable effectiveness of dataAll models are wrong
Setting up your workspace
Using Kaggle kernels
Running notebooks locallyInstalling TensorFlowInstalling KerasUsing data locally
Using the AWS deep learning AMI
Approximating functions
A forward pass
A logistic regressor
Python version of our logistic regressor
Optimizing model parameters
Measuring model loss
Gradient descentBackpropagationParameter updatesPutting it all together
A deeper network
A brief introduction to Keras
Importing KerasA two-layer model in KerasStacking layersCompiling the modelTraining the modelKeras and TensorFlow
Tensors and the computational graph
Exercises
Summary
2. Applying Machine Learning to Structured Data
The data
Heuristic, feature-based, and E2E models
The machine learning software stack
The heuristic approach
Making predictions using the heuristic modelThe F1 scoreEvaluating with a confusion matrix
The feature engineering approach
A feature from intuition – fraudsters don't sleepExpert insight – transfer, then cash outStatistical quirks – errors in balances
Preparing the data for the Keras library
One-hot encodingEntity embeddingsTokenizing categoriesCreating input modelsTraining the model
Creating predictive models with Keras
Extracting the targetCreating a test setCreating a validation setOversampling the training dataBuilding the modelCreating a simple baselineBuilding more complex models
A brief primer on tree-based methods
A simple decision treeA random forestXGBoost
E2E modeling
Exercises
Summary
3. Utilizing Computer Vision
Convolutional Neural NetworksFilters on MNISTAdding a second filter
Filters on color images
The building blocks of ConvNets in Keras
Conv2DKernel sizeStride sizePaddingInput shapeSimplified Conv2D notationReLU activationMaxPooling2DFlattenDenseTraining MNISTThe modelLoading the dataCompiling and training
More bells and whistles for our neural network
MomentumThe Adam optimizerRegularizationL2 regularizationL1 regularizationRegularization in KerasDropoutBatchnorm
Working with big image datasets
Working with pretrained models
Modifying VGG-16Random image augmentationAugmentation with ImageDataGenerator
The modularity tradeoff
Computer vision beyond classification
Facial recognitionBounding box prediction
Exercises
Summary
4. Understanding Time Series
Visualization and preparation in pandasAggregate global feature statisticsExamining the sample time series
Different kinds of stationarityWhy stationarity mattersMaking a time series stationaryWhen to ignore stationarity issues
Fast Fourier transformations
Autocorrelation
Establishing a training and testing regime
A note on backtesting
Median forecasting
ARIMA
Kalman filters
Forecasting with neural networks
Data preparationWeekdays
Conv1D
Dilated and causal convolution
Simple RNN
LSTM
The carry
Recurrent dropout
Bayesian deep learning
Exercises
Summary
5. Parsing Textual Data with Natural Language Processing
An introductory guide to spaCy
Named entity recognition
Fine-tuning the NER
Part-of-speech (POS) tagging
Rule-based matching
Adding custom functions to matchersAdding the matcher to the pipelineCombining rule-based and learning-based systems
Regular expressions
Using Python's regex moduleRegex in pandasWhen to use regexes and when not to
A text classification task
Preparing the data
Sanitizing charactersLemmatizationPreparing the targetPreparing the training and test sets
Bag-of-words
TF-IDF
Topic modeling
Word embeddings
Preprocessing for training with word vectorsLoading pretrained word vectorsTime series models with word vectors
Document similarity with word embeddings
A quick tour of the Keras functional API
Attention
Seq2seq models
Seq2seq architecture overviewThe dataEncoding charactersCreating inference modelsMaking translations
Exercises
Summary
6. Using Generative Models
Understanding autoencodersAutoencoder for MNISTAutoencoder for credit cards
Visualizing latent spaces with t-SNE
Variational autoencoders
MNIST exampleUsing the Lambda layerKullback–Leibler divergenceCreating a custom lossUsing a VAE to generate dataVAEs for an end-to-end fraud detection system
VAEs for time series
GANs
A MNIST GANUnderstanding GAN latent vectorsGAN training tricks
Using less data – active learning
Using labeling budgets efficientlyLeveraging machines for human labelingPseudo labeling for unlabeled dataUsing generative models
SGANs for fraud detection
Exercises
Summary
7. Reinforcement Learning for Financial Markets
Catch – a quick guide to reinforcement learningQ-learning turns RL into supervised learningDefining the Q-learning modelTraining to play Catch
Markov processes and the bellman equation – A more formal introduction to RL
The Bellman equation in economics
Advantage actor-critic models
Learning to balanceLearning to trade
Evolutionary strategies and genetic algorithms
Practical tips for RL engineering
Designing good reward functionsCareful, manual reward shapingInverse reinforcement learningLearning from human preferencesRobust RL
Frontiers of RL
Multi-agent RLLearning how to learnUnderstanding the brain through RL
Exercises
Summary
8. Privacy, Debugging, and Launching Your Products
Debugging dataHow to find out whether your data is up to the taskWhat to do if you don't have enough dataUnit testing dataKeeping data private and complying with regulationsPreparing the data for trainingUnderstanding which inputs led to which predictions
Debugging your model
Hyperparameter search with HyperasEfficient learning rate searchLearning rate schedulingMonitoring training with TensorBoardExploding and vanishing gradients
Deployment
Launching fastUnderstanding and monitoring metricsUnderstanding where your data comes from
Performance tips
Using the right hardware for your problemMaking use of distributed training with TF estimatorsUsing optimized layers such as CuDNNLSTMOptimizing your pipelineSpeeding up your code with CythonCaching frequent requests
Exercises
Summary
9. Fighting Bias
Sources of unfairness in machine learning
Legal perspectives
Observational fairness
Training to be fair
Causal learning
Obtaining causal modelsInstrument variablesNon-linear causal models
Interpreting models to ensure fairness
Unfairness as complex system failure
Complex systems are intrinsically hazardous systemsCatastrophes are caused by multiple failuresComplex systems run in degraded modeHuman operators both cause and prevent accidentsAccident-free operation requires experience with failure
A checklist for developing fair models
What is the goal of the model developers?Is the data biased?Are errors biased?How is feedback incorporated?Can the model be interpreted?What happens to models after deployment?
Exercises
Summary
10. Bayesian Inference and Probabilistic Programming
An intuitive guide to Bayesian inferenceFlat prior<50% priorPrior and posteriorMarkov Chain Monte CarloMetropolis-Hastings MCMCFrom probabilistic programming to deep probabilistic programming
Summary
Farewell
Further reading
General data analysisSound science in machine learningGeneral machine learningGeneral deep learningReinforcement learningBayesian machine learning
Other Books You May Enjoy
Leave a review - let other readers know what you think
Index

Content preview from Machine Learning for Finance

LSTM

In the last section, we learned about basic RNNs. In theory, simple RNNs should be able to retain even long-term memories. However, in practice, this approach often falls short because of the vanishing gradients problem.

Over the course of many timesteps, the network has a hard time keeping up meaningful gradients. While this is not the focus of this chapter, a more detailed exploration of why this happens can be read in the 1994 paper, Learning long-term dependencies with gradient descent is difficult, available at -https://ieeexplore.ieee.org/document/279181 - by Yoshua Bengio, Patrice Simard, and Paolo Frasconi.

In direct response to the vanishing gradients problem of simple RNNs, the Long Short-Term Memory (LSTM) layer was invented. This ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Publisher Resources

ISBN: 9781789136364

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills

Machine Learning for Finance

by James Le, Jannes Klaas

LSTM

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.