book

Build a Robo-Advisor with Python (From Scratch)

Name: Build a Robo-Advisor with Python (From Scratch)
ISBN: 9781633439672

by Alex Michalka, Robert Reider

April 2025

Beginner to intermediate

336 pages

10h 12m

English

Manning Publications

Read now

Unlock full access

Build a Robo-Advisor with Python (From Scratch)
copyright
contents
preface
acknowledgments
about this book
about the authors
about the cover
Part 1 Basic tools and building blocks
1 The rise of robo-advisors
1.1 What are robo-advisors?1.1.1 Key features of robo-advisors1.1.2 Comparison of robo-advisors1.1.3 Things robo-advisors don’t do1.2 Advantages of robo-advisors1.2.1 Low fees1.2.2 Tax savings1.2.3 Avoiding behavioral biases1.2.4 Saving time1.3 Example: Social Security benefits1.4 Python and robo-advising1.5 Who might be interested in learning about robo-advising?

2 An introduction to portfolio construction
2.1 A simple example with three assets2.2 Computing a portfolio’s expected return and standard deviation2.3 An illustration with random weights2.4 Introducing a risk-free asset2.5 Risk tolerance
3 Estimating expected returns and covariances
3.1 Estimating expected returns3.1.1 Historical averages3.1.2 CAPM3.1.3 Adjusting historical returns for changes in valuation3.1.4 Capital market assumptions from asset managers3.2 Estimating variances and covariances3.2.1 Using historical returns3.2.2 GARCH models3.2.3 Other approaches3.2.4 Subjective estimates
4 ETFs: The building blocks of robo-portfolios
4.1 ETF basics4.1.1 ETF strategies4.1.2 ETF pricing: Theory4.1.3 ETF pricing: Reality4.1.4 Costs of ETF investing4.2 ETFs vs. mutual funds4.2.1 Tradability4.2.2 Costs and minimums4.2.3 Tax efficiency4.2.4 The verdict on mutual funds vs. ETFs4.3 Total cost of ownership4.3.1 Cost components4.4 Beyond standard indices4.4.1 Smart beta4.4.2 Socially responsible investing
Part 2 Financial planning tools
5 Monte Carlo simulations
5.1 Simulating returns in Python5.2 Arithmetic vs. geometric average returns5.3 Simple vs. continuously compounded returns5.4 Geometric Brownian motion5.5 Estimating the probability of success5.6 Dynamic strategies5.7 Inflation risk5.8 Fat tails5.9 Historical simulations and booststrapping5.10 Longevity risk5.11 Flexibility of Monte Carlo simulations
6 Financial planning using reinforcement learning
6.1 A goals-based investing example6.2 An introduction to reinforcement learning6.2.1 Solution using dynamic programming6.2.2 Solution using Q-learning6.3 Utility function approach6.3.1 Understanding utility functions6.3.2 Optimal spending using utility functions6.4 Longevity risk6.5 Other extensions
7 Measuring and evaluating returns
7.1 Time-weighted vs. dollar-weighted returns7.1.1 Time-weighted returns7.1.2 Dollar-weighted returns7.2 Risk-adjusted returns7.2.1 Sharpe ratio7.2.2 Alpha7.2.3 Evaluating an ESG fund’s performance7.2.4 Which is better, alpha or Sharpe ratio?
8 Asset location
8.1 A simple example8.2 The tax efficiency of various assets8.3 Adding a Roth account8.3.1 A simple example with three types of accounts8.3.2 An example with optimization8.4 Additional considerations
9 Tax-efficient withdrawal strategies
9.1 The intuition behind tax-efficient strategies9.1.1 Principle 1: Deplete less tax-efficient accounts first9.1.2 Principle 2: Keep tax brackets stable over time9.2 Examples of sequencing strategies9.2.1 Starting assumptions9.2.2 Tax-sequencing code9.2.3 Strategy 1: IRA first9.2.4 Strategy 2: Taxable first9.2.5 Strategy 3: Fill lower tax brackets9.2.6 Strategy 4: Roth conversions9.3 Additional complications9.3.1 Required minimum distributions9.3.2 Inheritance9.3.3 Capital gains taxes9.3.4 State taxes9.3.5 Putting it all together
Part 3 Portfolio construction
10 Optimization and portfolio construction
10.1 Convex optimization in Python10.1.1 Basics of optimization10.1.2 Convexity10.1.3 Python libraries for optimization10.2 Mean-variance optimization10.2.1 The basic problem10.2.2 Adding more constraints10.3 Optimization-based asset allocation10.3.1 Minimal constraints10.3.2 Enforcing diversification10.3.3 Creating an efficient frontier10.3.4 Building an ESG portfolio
11 Asset allocation by risk: Introduction to risk parity
11.1 Decomposing portfolio risk11.1.1 Risk contributions11.1.2 Risk concentration in a “diversified” portfolio11.1.3 Risk parity as an optimal portfolio11.2 Calculating risk-parity weights11.2.1 Naive risk parity11.2.2 General risk parity11.2.3 Weighted risk parity11.2.4 Hierarchical risk parity11.3 Implementation of risk-parity portfolios11.3.1 Applying leverage
12 The Black–Litterman model
12.1 Equilibrium returns12.1.1 Reverse optimization12.1.2 Understanding equilibrium12.2 Conditional probability and Bayes’ rule12.3 Incorporating investor views12.3.1 Expected returns as random variables12.3.2 Expressing views12.3.3 Updating equilibrium returns12.3.4 Assumptions and parameters12.4 Examples12.4.1 Example: Sector selection12.4.2 Example: Global allocation with cryptocurrencies
Part 4 Portfolio management
13 Rebalancing: Tracking a target portfolio
13.1 Rebalancing basics13.1.1 The need for rebalancing13.1.2 Downsides of rebalancing13.1.3 Dividends and deposits13.2 Simple rebalancing strategies13.2.1 Fixed-interval rebalancing13.2.2 Threshold-based rebalancing13.2.3 Other considerations13.2.4 Final thoughts13.3 Optimizing rebalancing13.3.1 Variables13.3.2 Inputs13.3.3 Formulating the problem13.3.4 Running an example13.4 Comparing rebalancing approaches13.4.1 Implementing rebalancers13.4.2 Building the backtester13.4.3 Running backtests13.4.4 Evaluating results
14 Tax-loss harvesting: Improving after-tax returns
14.1 The economics of tax-loss harvesting14.1.1 Tax deferral14.1.2 Rate conversion14.1.3 When harvesting doesn’t help14.2 The wash-sale rule14.2.1 Wash-sale basics14.2.2 Wash sales with Python14.3 Deciding when to harvest14.3.1 Trading costs14.3.2 Opportunity cost14.3.3 End-to-end evaluation14.4 Testing a TLH strategy14.4.1 Backtester modifications14.4.2 Choosing ETFs

Content preview from Build a Robo-Advisor with Python (From Scratch)

12 The Black–Litterman model

This chapter covers

Understanding the Black–Litterman model for asset allocation
Implementing the Black–Litterman model in Python
Examples of the model in action, including one with cryptocurrency as an asset class

In chapter 10, we learned how to use convex optimization to build portfolios. The key inputs to these optimization problems are the expected returns of the assets and the covariance matrix of asset returns. We saw that portfolios obtained via optimization can be very sensitive to the expected returns inputs.

The Black–Litterman model, developed by Fischer Black and Robert Litterman while working at Goldman Sachs in the early 1990s, aims to accomplish two goals:

Address the sensitivity of portfolio ...

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: 9781633439672Publisher Support Publisher Website Errata Page

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills

Build a Robo-Advisor with Python (From Scratch)

by Alex Michalka, Robert Reider