Implementing Machine Learning for Finance: A Systematic Approach to Predictive Risk and Performance Analysis for Investment Portfolios

By Tshepo Chris Nokeri

Bring together machine learning (ML) and deep learning (DL) in financial trading, with an emphasis on investment management. This book explains systematic approaches to investment portfolio management, risk analysis, and performance analysis, including predictive analytics using data science procedures.
The book introduces pattern recognition and future price forecasting that exerts effects on time series analysis models, such as the Autoregressive Integrated Moving Average (ARIMA) model, Seasonal ARIMA (SARIMA) model, and Additive model, and it covers the Least Squares model and the Long Short-Term Memory (LSTM) model. It presents hidden pattern recognition and market regime prediction applying the Gaussian Hidden Markov Model. The book covers the practical application of the K-Means model in stock clustering. It establishes the practical application of the Variance-Covariance method and Simulation method (using Monte Carlo Simulation) for value at risk estimation. It also includes market direction classification using both the Logistic classifier and the Multilayer Perceptron classifier. Finally, the book presents performance and risk analysis for investment portfolios.
By the end of this book, you should be able to explain how algorithmic trading works and its practical application in the real world, and know how to apply supervised and unsupervised ML and DL models to bolster investment decision making and implement and optimize investment strategies and systems.

What You Will Learn

• Understand the fundamentals of the financial market and algorithmic trading, as well as supervised and unsupervised learning models that are appropriate for systematic investment portfolio management
• Know the concepts of feature engineering, data visualization, and hyperparameter optimization
• Design, build, and test supervised and unsupervised ML and DL models
• Discover seasonality, trends, and market regimes, simulating a change in the market and investment strategy problems and predicting market direction and prices
• Structure and optimize an investment portfolio with preeminent asset classes and measure the underlying risk

Who This Book Is For
Beginning and intermediate data scientists, machine learning engineers, business executives, and finance professionals (such as investment analysts and traders)

• Language: English
• Publisher: Apress
• Release date: May 26, 2021
• ISBN: 9781484271100

Book preview

© The Author(s), under exclusive license to APress Media, LLC, part of Springer Nature 2021

T. C. NokeriImplementing Machine Learning for Financehttps://doi.org/10.1007/978-1-4842-7110-0_1

1. Introduction to Financial Markets and Algorithmic Trading

Tshepo Chris Nokeri¹  

(1)

Pretoria, South Africa

This is the initial chapter of a book that presents algorithmic trading. This chapter carefully covers the foreign exchange (FX) market and the stock market. It explores how we pair, quote, and exchange official currencies. Subsequently, it covers the stock exchange. In addition, it presents key market participants, principal brokers, liquidity providers, modern technologies, and software platforms that facilitate the exchange of currencies and shares. Furthermore, it looks at the speculative nature of the FX market and stock exchange market and specific aspects of investment risk management. Last, it covers several machine learning methods that we can apply to combat problems in finance.

FX Market

The FX market represents an international market in which investors exchange currency for another. It does not have a principal visible location in which transactions occur, each investor holds their own transaction records, and each transaction happens electronically. Key market participants self-regulate using guidelines prescribed by a regulatory body within their geographic boundaries.

Exchange Rate

Each official country generally has its own currency. The currency is a class of payments administered and distributed by the central government and dispersed around their geographic boundaries. In relation to foreign trade, an individual or corporation that purchases foreign goods or services and sells them to their local market typically has to exchange currencies. We universally recognize an exchange rate as the ratio of the price of a local currency to a foreign currency. The major currencies include the US dollar ($), euro (€), Great Britain pound (£), Japanese yen (¥), etc. The cross rate is the price of a currency against another, where the US dollar is uninvolved. For instance, euro/GBP is a cross rate between the euro and the sterling.

Exchange Rates Quotation

An exchange rate represents the price of a currency relative to an alternative. We quote currencies directly or indirectly. Using the direct method, the exchange shows how much we have to exchange the local currency for one unit of a foreign currency. For instance, EUR/USD = 1.19. The indirect method shows how much foreign currency trades for one unit of the local currency. For instance, USD/EUR = 0.84.

Exchange Rate Movement

The exchange rate is inconstant; it varies over time. There are several prime factors that influence changes in the exchange rate. For instance, economic and growth factors such as gross domestic product growth (GDP), inflation rates (consumer price index or GDP deflator), and stocks traded, external debt stocks, current account balance, total reserves, etc. In other instances, rates may react to geopolitical news, natural disasters, labor union activities, social-unrest, corporate scandals, among others. When changes befall, we say that one currency is stronger or weaker than another currency. For instance, with the EUR/USD currency pair, if the euro strengthens, the USD progressively weakens. Let’s say EUR/USD opened at 1.2100 and closed at 1.2190; we say that the EUR strengthened since 1 EUR bought more USD at the close than at open.

Assuming an investor buys 1 million euros at 1.2100 at the open, assuming it will strengthen on that day, but the euro closes at 1.2190, the investor has experienced $7 383. 10(€9000) loss.

$$ Euro\ Loss=\frac{+\$1\ 000\ 0000=-\$1\ 000\ 000=\kern0.5em }{-0-}\frac{-\text{\EUR} 1\ 219\ 000+\text{\EUR} 1\ 210\ 000\ }{\text{\EUR} 9\ 000} $$

Bids and Offers

A market maker represents an organization that exchanges currencies on its own account at prices reflected on their systems. Common market makers include banks and brokers. They quote two rates as follows:

Bid: The rate at which market makers buy the currency

Offer: The rate at which market makers sell the base currency

The Left Bid and Right Offer Rule

As tricky as it may be when market makers trade, they are buying and selling at the same time. They buy the base currency on the left side of the quote and sell the currency on the right side of the quote. For instance, if a market maker quotes the EUR/USD at 1.2100/15, they will buy the dollars at €1.2100 and sell them at €1.2115.

The difference between the bid and offer is called the spread. It informs us about liquidity. The more liquid the market, the more narrow the spread. To understand how this works, let’s look at the minor currency pairs and major currencies. Currency pairs in emerging markets such as South African rand to rupees (ZAR/INR), Bangladeshi taka to Omani rial (BDT/OMR), among others, have low trading activities and are traded in small quantities. This results in higher spreads when compared to major currencies such as the GBP to the US dollar (USD), Australian dollar to the US dollar, etc. Equation 1-1 shows how we find the spread.

$$ Spread= Bid- Ask $$

(Equation 1-1)

Consider the scenario where the EUR/USD is quoted at 1.2100/15; the spread equals 0.015.

The margin represents the difference between the bid and ask divided by the ask. It can be written mathematically as in Equation 1-2.

$$ Margin=\kern0.5em \left( Bid- Ask\right)/ Ask\kern0.5em \ast 100\% $$

(Equation 1-2)

Margin equals 1.2381 percent.

Assume you are a US tourist who is visiting Europe and wants euros; you must buy the euros using the US dollars you arrived with. The market makers will sell them to you at €1.2115. In contrast, if you are on the seller’s side, the market maker buys the currency at