Ned Krastev

Python for Finance

365 DATA SCENCE 2

Table of Contents
Abstract .................................................................................................................................... 3
1. Calculating and Comparing Rates of Return in Python .................................................. 4
1.1 Upside and Downside ................................................................................................. 4
1.2 Calculating Rates of Return ..........................................................................................5
1.3 Portfolios of Stocks ....................................................................................................... 5
1.4 Market Indices ............................................................................................................... 6
2. Measuring Investment Risk ................................................................................................ 7
2.1 The Relationship between Securities ........................................................................ 7
2.2 Calculating Covariance and Correlation ................................................................... 8
2.3 Calculating Portfolio Variance .................................................................................... 9
3. Using Regression for Financial Analyses ........................................................................ 10
3.1 Regression Analysis ...................................................................................................11
3.2 How Good is a Regression? ....................................................................................... 12
4. Markowitz Portfolio Optimization ..................................................................................12
4.1 Efficient Frontier ..............................................................................................................13
5.The Capital Asset Pricing Model .......................................................................................... 14
5.1 Sharpe Ratio ...................................................................................................................16
5.2 Achieving Alpha .........................................................................................................16
5.3 Types of Investment Strategies ...................................................................................16
6.Monte Carlo Simulations ................................................................................................... 17
6.1 Monte Carlo in Corporate Financial Setting ............................................................ 17
6.2 Asset Pricing with Monte Carlo ................................................................................. 18
7. Derivative Instruments .........................................................................................................20
7.1 Future/Forward Contracts ..........................................................................................21
7.2 Option Contracts ........................................................................................................22
7.3 Swap Contracts ..........................................................................................................24
7.4 Pricing Derivatives ......................................................................................................25
365 DATA SCENCE 3

Abstract

Python for Finance is the crossing point where programming in Python blends
with financial theory. Together, they give you the know-how to apply that theory
into practice and real-life scenarios. In a world where individuals and companies are
aiming to become more and more autonomous, your ability to combine programming
skills with financial data will allow you to create independent analyses. And that
competency will give you an edge over your competitors or in your personal
investments. To prepare you for these multi-faceted challenges, these course notes
provides the relevant topics in financial theory and their hands-on application in

Python. You will learn to :

• Calculate and compare rates of return in Python
• Use Monte Carlo simulations as a decision-making tool
• Use regressions for financial analysis
• Apply the Markowitz Portfolio Theory
• Work with multivariate regression analysis

Keywords: Python for Finance, Monte Carlo , financial analyses , regression, Markowitz
Portfolio Theory
365 DATA SCENCE 4

1. Calculating and Comparing Rates of Return in Python

1.1 Upside and Downside

When we think of an investment, we have to remember two things – its upside and
its downside. In other words, we should consider the profit that will be made if
everything goes well and the risk of losses if the investment is unsuccessful.

Type of asset Definition

Government bonds Government bonds offer an average rate of return

of 3%, and historically, there have been very few
cases of governments going bankrupt and not
repaying what’s owed to investors. So, some risk
comes with this investment; it isn’t risk-free, but
the risk is very contained.

Equity shares Equity shares have a higher rate of return –

approximately 6%. However, they are associated
with much more frequent fluctuations and
price changes, as different variables influence a
company’s share price.

The art of finance isn’t about maximizing an investor’s returns in a year. It is about
making informed decisions that consider both dimensions, risk and return, and
optimizing the risk-return combination of an investment portfolio.
365 DATA SCENCE 5

1.2 Calculating Rates of Return

Type of asset Definition

Simple returns (Ending Price – Beginning Price) / (Beginning

Price)

Preferable when you have to deal with multiple

assets over the same timeframe

Log returns Log (Ending Price / Beginning Price)

Preferable when you make calculations about a

single asset over time

1.3 Portfolios of Stocks

Most investors own several stocks, and the set of stocks that an investor owns is called
his investment portfolio.

Investment Portfolio

Stock A Stock B Stock C

Stock 1 Stock 2 Stock 3

Calculating the rate of return of a portfolio is an easy and intuitive task. We have the
rates of return of individual securities, and we only have to multiply each security’s rate
of return by the weight it has in the overall portfolio.
365 DATA SCENCE 6

1.4 Market Indices

A market index provides an idea about how a given stock market is performing. It
represents a large enough sample of the overall number of stocks in that market and
can be considered a good enough proxy of the overall development of the market.

Market Index Description

S&P500 Comprises 500 of the largest listed companies.

The diverse constituency of the S&P 500 makes it
a true approximation of the US stock market. It is
a market-cap-weighted index, so companies are
weighted according to their market value
Dow Jones Industrial The Dow Jones industrial average index uses an
Average average of 30 large public stocks traded in the US
market

NASDAQ Most companies that are part of the NASDAQ

index are information technology companies,
and NASDAQ gives us an idea about the general
development of the tech industry

A stock index gives you a sense of the type of return you can expect if you invest in
a well-diversified portfolio in a given market.
365 DATA SCENCE 7

2. Measuring Investment Risk

Variability plays an important role in the world of finance. It is the best measure of risk
we have. A volatile stock is much more likely to deviate from its historical returns and
surprise investors negatively.

s2 = ∑ (x-x)2 / n-1
Sample variance Standard deviation

Commonly used statistical measures, such as variance and standard deviation, can
help us a great deal when we try to quantify risk associated with the dispersion in the
likely outcome. Such dispersion is measured by a security’s variance and standard
deviation.

2.1 The Relationship between Securities

It is reasonable to expect the prices of shares in a stock exchange are influenced

by common factors. The most obvious example is the development of the economy.
In general, favorable macroeconomic conditions facilitate the business of all
companies.

Busines
Jobs

Consumer spending
365 DATA SCENCE 8

Companies’ shares are influenced by the state of the economy. However, different
industries are influenced in a different way. Some industries do better than others in
times of crisis.

There is a relationship between the prices of different companies, and it is

very important to understand what causes this relationship and how to use this
measurement to build optimal investment portfolios.

2.2 Calculating Covariance and Correlation

Calculating
Covariance:

Calculating
Correlation:

Market Index Description

Perfect correlation Equal to 1. The entire variability of the second

variable is explained by the first variable

Negative correlation It can be perfect negative correlation of -1 or

much likelier an imperfect negative correlation of
a value between -1 and 0

Neutral correlation A correlation of 0 between two variables means

they are independent from each other
365 DATA SCENCE 9

2.3 Calculating Portfolio Variance

If a portfolio contains two stocks, its risk will be a function of the variances of the two
stocks and of the correlation between them.

Type of risk Description

Systematic risk This is the uncertainty that is characteristic of the

entire market. Systematic risk is made of the day
to day changes in stock prices and is caused by
events that affect all companies

Unsystematic risk These are company-specific, even industry-

specific, risks that can be smoothed out through
diversification
365 DATA SCENCE 10

3. Using Regression for Financial Analyses

3.1 Regression Analysis

Regression analysis is one of the most frequently used tools in the world of finance.
It quantifies the relationship between a variable, called dependent variable, and one
or more explanatory variables, also called independent variables.

Type of regression Description

Simple regressions

Regression analysis assumes the existence of a

linear relationship between the two variables. One
straight line is the best fit and can help us describe
the rapport between all the data points we see in
the plot

Multivariate regressions

By considering more variables in the regression

equation, we’ll improve its explanatory power
and provide a better idea of the full picture of
circumstances that determine the development of
the variable we are trying to predict
365 DATA SCENCE 11

In order to calculate regression coefficients, we are estimating a best fitting line

minimizing the sum of squared residuals.

$ 1,400,000

$ 1,200,000

$ 1,000,000
Price (y)

$ 800,000

$ 600,000
Estimation
$ 400,000 error

$ 200,000

50
0 200 400 600 800 1000 1200

Size (x)

Minimizing residuals (the amount of estimation error) in a simple regression setting

240
210
200
180
Y1 160
140
120
50

70 60 90
50 40 70 80
30 20 40 50 60
10 20 30 X3
X1

Minimizing residuals (the amount of estimation error) in a multivariate regression

setting

Simple regression Multivariate regression

365 DATA SCENCE 12

3.2 How Good is a Regression?

Statisticians have come up with a tool that’s easy to understand. It is called R2.
To understand R2, we need to think of the total variability of the data. TSS provides a
sense of the variability of the data. The formula for the variance of x is the same,
but N – 1 is omitted.

The total variability of the data can also be decomposed as:

where SSE is the sum of the squares that were explained, and SSR is the sum of the
squared residuals (unexplained)

4. Markowitz Portfolio Optimization

Typically, R square is looked at as a percentage value, and it can range from 0% to

100%. The higher it is, the greater the explanatory power of the regression model
(the lower the weight of unexplained squares, the better the model).
365 DATA SCENCE 13

4.1 Efficient Frontier

Markowitz proved the existence of an efficient set of portfolios that optimize

investors’ return for the amount of risk they are willing to accept.
One of the most important highlights of his work is that investments in multiple
securities shouldn’t be analyzed separately, but should be considered in a portfolio,
and financiers must understand how different securities in a portfolio interact with
each other.

Portfolios 1-6 Markowitz Shape

10.0%

9.5%

9.0%

8.5%
Return

8.0%

7.5%

7.0%

6.5%

6.0%
4.0% 5.0% 6.0% 7.0% 8.0% 9.0%

Standart deviation

Markowitz suggested that through the combination of securities with low

correlation, investors can optimize their returns without assuming additional risk.
365 DATA SCENCE 14

5. The Capital Asset Pricing Model

William Sharpe’s Capital Asset Pricing Model contains:

Market Index Description

Market portfolio A bundle of all possible investments in the world

(both bonds and stocks), and the risk-return
combination of this portfolio is superior to the one
of any other portfolio

Risk-free asset An investment with no risk (zero standard

deviation). It has a positive rate of return, but zero
risk associated with it

Beta coefficient It helps us quantify the relationship between a

security and the overall market portfolio

Capital Market Line The line that connects the risk-free rate and
is tangent to the efficient frontier is called the
Capital Market Line. The point where the Capital
Market Line is tangent to the efficient frontier is
the market portfolio
365 DATA SCENCE 15

Expecter Returns Capital Market Line

Efficient Frontier
Tangency Portfolio

Individual Assets

risk free race

Standart Deviation

• The Tangency portfolio is the Market portfolio

• Individual assets (portfolios of assets) that are not lying on the efficient frontier are
inefficient
• The risk-free rate has a standard deviation of 0
• The tangency portfolio lies on the Capital Market Line
• Once we introduce a risk-free asset, all investors would be interested in buying
only two assets – the risk-free asset and the Market portfolio (the Tangency
portfolio)

The CAPM formula:

A security’s expected return is equal to the return of the risk-free asset plus beta times
the expected return of the market minus the return of the risk-free asset.

Risk-free: The minimum amount of compensation an investor would expect from an

investment

Beta coefficient: How risky is the specific asset with respect to the market

Market Risk Premium: The amount of compensation an investor would expect when
buying the Market portfolio
365 DATA SCENCE 16

5.1 Sharpe Ratio

The Sharpe ratio formula:

Rational investors want to maximize their rate of return and minimize the risk of their
investment, so they need a measure of risk-adjusted return, a tool that would allow
them to compare different securities, as they will be interested in investing in the ones
that will provide the highest return for a given amount of risk.

This is how William Sharpe came up with his famous Sharpe ratio. It is a great way to
make a proper comparison between stocks and portfolios and decide which one is
preferable in terms of risk and return.

5.2 Achieving alpha

What is alpha?

In the world of finance and investments, alpha is often thought of as a measure of how
good (or poor) the performance of a fund manager has been. The standard CAPM
setting assumes efficient financial market and an alpha of 0. Given that beta multiplied
by the equity risk premium gives us the compensation for risk that’s been taken with
the investment, alpha shows us how much return we get without bearing extra risk. A
great portfolio manager, someone who outperforms the market, can achieve a high
alpha. And conversely, a poor investment professional may even obtain a negative
alpha, meaning he underperformed the market.

5.3 Types of Investment Strategies

Type of correlation Description

Passive Investing Consists in buying a portfolio of assets and holding it in

the long-run regardless of short-term macroeconomic
developments
Active Investing Frequent trading based on expectations regarding
macroeconomic and company-specific developments,

Arbitrage Trading Find pricing discrepancies on the market and exploit these
discrepancies in order to make a profit without assuming risk
Value Investing Invest in specific companies, hoping they will outperform
their peers
365 DATA SCENCE 17

6. Monte Carlo Simulations

Simulated Asset Paths
58

56

54
Asset Price

53

50

48

46

44

50 45 40 35 30 25 20 15 10 5 0

Time to Expiry

When we run a Monte Carlo simulation, we are interested in observing the different
possible realizations of a future event. What happens in real life is just one of the
possible outcomes of any event.
And that’s where a Monte Carlo simulation comes in handy. We can use past data,
something we already know, to create a simulation – a new set of fictional but sensible
data. These realizations are generated by observing the distribution of the historical
data and calculating its mean and variance.
Such information is valuable, as it allows us to consider a good proxy of the probability
of different outcomes and can help us make an informed decision.

6.1 Monte Carlo in a Corporate Finance Setting

Type of correlation Description

Revenues Current revenues = Previous revenues * (1 + growth rate)

Growth rate is the unknown variable. We can simulate its

development if we know its distribution, mean, and standard
deviation. This would allow us to obtain multiple simulations
about the development of revenues
Cost of Cost of goods sold = Percentage of revenues; For each
goods sold “revenue path” Cogs can be simulated as a percentage
of the observed amount of revenues. All we have to do is
simulate the percentage as a random variable with a known
distribution, mean, and standard deviation
Gross profit Revenues – Cost of goods sold = Gross profit
365 DATA SCENCE 18

Type of correlation Description

Revenues Current revenues = Previous revenues * (1 + growth rate)

Growth rate is the unknown variable. We can simulate

its development if we know its distribution, mean, and
standard deviation. This would allow us to obtain multiple
simulations about the development of revenues
Cost of goods sold Cost of goods sold = Percentage of revenues; For each
“revenue path” Cogs can be simulated as a percentage
of the observed amount of revenues. All we have to do is
simulate the percentage as a random variable with a known
distribution, mean, and standard deviation
Gross profit Revenues – Cost of goods sold = Gross profit

6.2 Asset Pricing with Monte Carlo

The price of a share today is equal to the price of the same share yesterday multiplied
by the log return of the share (r). Remember that:

e in(x) = x
So, above we have written:
Price Today
in ( )
Price Yesterday

Which is equal to:

365 DATA SCENCE 19

We know yesterday’s stock price. We don’t know r, as it is a random variable. Brownian

motion is a concept that would allow us to model such randomness. The formula we
can use is made of two components:

Drift Random component

365 DATA SCENCE 20

7. Derivative Instruments

Originally, derivatives served as a hedging instrument. Companies interested in

buying these contracts were mostly concerned about protecting their investment.
However, with time, financial institutions introduced a great deal of innovation to the
scene, the so-called financial engineering was applied, and new types of derivatives
appeared.

Type of correlation Description

Forwards A forward contract is used when two parties agree

that one party will sell to the other an underlying
asset at a future point of time. The price of the
asset is agreed beforehand.

Futures Futures are highly standardized forward contracts

typically stipulated in a marketplace. The
difference between futures and forwards is the
level of standardization and the participation of a
clearing house – the transaction goes through the
marketplace, and the counterparties do not know
each other.
Swaps Swap contracts are derivative instruments in which
two parties agree to exchange cash flows, based
on an underlying asset at a future point of time.
The underlying asset can be an interest rate, a
stock price, a bond price, a commodity price, and
so on.

Options An option contract enables its owner to buy or

sell an underlying asset at a price, also known as
strike price. The owner of the option contract may
buy or sell the asset at the given price, but he may
also decide not to do it if the asset’s price isn’t
advantageous.
365 DATA SCENCE 21

7.1 Forward / Future contracts

The two parties enter into an agreement to buy/sell an asset at time T.

Contract
Today A B

Side A Side B

Money
A B

Side A Asset Side B

A forward/future contract has the following payoff:

Payoff

The payoff of a forward/future contract is a function of the agreed price when the
contract is signed (K), and the price of the asset at time t
365 DATA SCENCE 22

7.2 Option Contracts

There are two main types of options.

Call Options – the holder has the right to buy an asset at an agreed strike price.

Put Options – the holder has the right to sell an asset at an agreed strike price

Contract
Today A B

Side A Side B

Money
A B

Side A Asset Side B

At time T, the owner of the option decides whether to exercise it or not:

Scenario 1: Exercise

K
A B

Side A St Side B

Scenario 2: Don’t exercise

Don’t do
A anything B

Side A Side B
365 DATA SCENCE 23

A call option contract has the following payoff:

Payoff

The payoff of an option is a function of the agreed strike price when the contract
is signed (K), and the price of the asset at the time of maturity of the option (St). In
addition, there are two types of options – European and American. European options
can be exercised only at maturity, while American options can be exercised at any time
and are hence more valuable.

A put option contract has the following payoff:

Payoff

The payoff of an option is a function of the agreed strike price when the contract
is signed (K), and the price of the asset at the time of maturity of the option (St). In
addition, there are two types of options – European and American. European options
can be exercised only at maturity, while American options can be exercised at any time
and are hence more valuable.
365 DATA SCENCE 24

7.3 Swap Contracts

In a swap contract, the two parties agree to exchange cash flows based on an
underlying asset.

Contract
Today A B

Side A St Side B

Asset 1

t=T A B

Asset 2
Side A Side B

Cash flow = Price of Asset 1 – Price of Asset 2

A swap contract has the following payoff:

Payoff

The payoff of a swap is a function of the price of the underlying asset.

 365 DATA SCENCE 25

7.4 Pricing Derivatives

The Black Scholes formula is one of the most widely used tools for derivatives pricing.
It can be written in the following way:

Type of correlation Description

S The stock’s current market price

K The strike price at which the option can be

exercised; if we exercise the option, we can buy
the stock at the strike price K

T-t The option’s time until expiration

r Risk-free rate

The Black Scholes formula is one of the most widely used tools for derivatives pricing.
It can be written in the following way:

Type of correlation Description

S The standard deviation of the underlying asset

N Normal distribution

Copyright 2022 365 Data Science Ltd. Reproduction is forbidden unless authorized. All rights reserved.
 Learn DATA SCIENCE
anytime, anywhere, at your own pace.

If you found this resource useful, check out our e-learning program. We have
everything you need to succeed in data science.

Learn the most sought-after data science skills from the best experts in the field!
Earn a verifiable certificate of achievement trusted by employers worldwide and
future proof your career.

Comprehensive training, exams, certificates.

 162 hours of video  Exams & Certification  Portfolio advice

 599+ Exercises  Personalized support  New content
 Downloadables  Resume Builder & Feedback  Career tracks

Join a global community of 1.8 M successful students with an annual subscription

at 60% OFF with coupon code 365RESOURCES.

$432 $172.80/year

Start at 60% Off

 Ned Krastev

Email: team@365datascience.com