Final project analyse stock price fluctuations according to market, internal business factors and forecast the price of apple’s stock

UNIVERSITY OF INFORMATION TECHNOLOGY INFORMATION SYSTEM FACULTY o0o fH FINAL PROJECT ANALYSE STOCK PRICE FLUCTUATIONS ACCORDING TO MARKET, INTERNAL BUSINESS FACTORS AND FORECAST THE P

UNIVERSITY OF INFORMATION TECHNOLOGY INFORMATION SYSTEM FACULTY

o0o

fH

FINAL PROJECT

ANALYSE STOCK PRICE FLUCTUATIONS ACCORDING TO MARKET, INTERNAL BUSINESS FACTORS AND FORECAST

THE PRICE OF APPLE’S STOCK

Subject! DATA ANALYTICS IN BUSINESS Lecturer: Dr.Tran Van Hai Triéu

Nguyen Dang Hoang Ha <21520577>

Dao Gia Hai <21520577>

Doan Van Anh Hién <21520577>

Class: IS403.012.TMCL

Ho Chi Minh City, November 10, 2023

Acknowledgement

Firstly, we would like to express our sincerest gratitude to Professor Tran Van Hai Trieu, lecturer of the Information Systems Faculty at the University of Infor- mation Technology The professor has been wholeheartedly supportive, providing direct guidance and instructions throughout our research and study process Dur- ing our time studying under him, we not only acquired valuable knowledge but also developed a serious and effective work ethic and research attitude These qualities are essential for our future academic and professional endeavors

However, we acknowledge that our technical knowledge is still limited, and each team member lacks practical experience Therefore, the content of this report may have certain shortcomings We sincerely hope to receive your feedback and addi- tional guidance, Professor, to further improve our expertise This will enable us

to enhance the quality of this report and support the execution of future research projects

Ho Chi Minh City, November 2023 Student Group

Man Ngo Thuy Tien Tran Tinh Minh Tu

Le Bao Chau Nguyen Dang Hoang Ha Dao Gia Hai

Doan Van Anh Hien

Teacher’s Feedback

AGENDA

1

2

REASON FOR CHOOSING THE TOPIC

RESEARCH OBJECTIVES

RESEARCH METHODOLOGY

THEORETICAL FRAMEWORK AND RELATED REPORTS

4.1 Models and Functions Theoretical Background

4.1.1 Descriptive Analysis .02 5

4.1.2 ARIMAModel

413 LSTMModel

42 LSTMIIH2]

4.2.1 Forgetafe: ee 4.2.2 InputGate: 2 ee 4.2.3 OutputGate: 2.2.2 2 ee 42.4 AdvantagesofLSTM

42.5 DisadvantagesofLSTM

COMPANY INTRODUCTION 5.1 OverviewofApple Q Q Q Q o 5.2 Apple StockReVileW ee DATASET AND DEPLOYMENT 6.1 Introduction to the collecteddataset

6.1.1 Dataset] 2.2.0.0 2.0.0.0 00000004

6.1.2 Dataset2 2 2.0.0.0 00 2 es APPLE STOCK PRICE ANALYSIS FROM 2019 TO 2023 7.1 Statistical Result 2 ee ee 7.1.1 Mean, Median, Mode, Variance, Standard Deviation, Range, Quartiles, Standard Error of Mean, Skewness, and Kurto- sis of Close Price 2 ee 7.1.2 ANOVA,Regresion

7.2 Descriptive Analysis 2 0.2 02200 2s 72.1 Mean, Median, Max,Min .00

7.22 Variance, Standard Deviation

723 SkewnessKurtoSIS

7.3 Analysis of dependent factors (CPI,etc)

7.3.1 ANOVA,REGRESSION

10

10

10

12

13

13

15

15

16

16

17

8 STOCK PRICE PREDICTION USING ARIMA AND LSTM (2000-

List of photos

1 Apples Business Modell3] 19

2 Appless Business Revenue By Sourcel4|_ 19

3 Appless Business Revenue By Countrv[4] 20

4 The proportion of Apple in the S&P 500index 20

5 The rate of return on the stocks of major U.S technology companies 21 6 Result of Excel 2 ee 25 7 Resultof SPSS 2019 2.2 2 ee 25 8 Resultof SPSS 2020 .2.2020200202002.2 002 26 9 Resultof SPSS 2021 26

10 Result of SPSS 2022 2.2 ee 27 11 Result of SPSS 2023 2 ee 27 12 ResultofPython20192023 28

13 Result of R 2019-2023 2 ee 28 14 ANOVA - Regression - ResultofExcel 29

15 ANOVA - Regression -ResultofR 29

16 ANOVA - Regression - ResultofPython 30

17 Mean, Median, Max, Min ofClosePrice 30

18 Chart Displaying Revenue, Net Income, and Profit Margin Percent- age for Apple (2019-2023) 31

19 Chart Displaying Revenue, Net Income, and Profit Margin Percent- age for Apple (2019-2023) 32

20 Closing Price Mean of Apple (2019-2023) 33

21 HflaionIndexin2020 36

22 EFED Interest Rate Decisionin2020 37

23 FED Interest Rate Decisionin2020 37

24 Skewness, Kurtosis Result2019 38

25 Skewness, Kurtosis Result2020 39

26 Skewness, KurtosisResult2021 40

27 Skewness, Kurtosis Result 2022 Al 28 Skewness, Kurtosis Result 2023 42

29 Inflation Anova Result 2023 43

30 US Dollar Index Close Anova Result2023 43

31 FEDRate AnovaResult2023 44

32 CPlIAnovaResult2023 44

33 Unrate AnovaResult2023 45

34 RegressionResult20232 45

35 New Regression Result2023 46

38

39

40

41

42

43

44

45

46

AutoArima ResultsChart 56

MAERMSE of AutoArima 57

LŠTM Results Chat 57

LŠTM Results Chat 57

LŠTM Results Chat 58

ROA from 2019-2023 - Source: Applecom 59 ROA Apple between with FAANG from 2019-2023 - Source: Ap-

1 REASON FOR CHOOSING THE TOPIC

Researching the stock market is one of the crucial and challenging issues It’s an interesting problem that has drawn the attention of researchers and investors alike, spanning from the past to the present To serve our academic project and broaden our knowledge of corporate finance, our team has chosen the topic "Analyzing Stock Price Fluctuations According to Market and Internal Business Factors and Forecasting the Profit of Apple’s Stock." This choice aims to explore the influence

of micro and macroeconomic factors on stock prices

Apple Inc is a globally successful technology company The historical volatil- ity of Apple’s stock, influenced by various market forces and internal business decisions, provides an exciting opportunity to investigate the complex relationship between external and internal factors affecting stock prices

In this study, we will utilize stock market data from the past five years to ex- amine what the stock prices reflect about the financial situation of the company Additionally, we will construct time series models using ARIMA and LSTM mod- els to meet the demand for predicting stock prices in the future

2 RESEARCH OBJECTIVES

Overall objective: Get to know more about business analysis and the way anal- ysis and prediction algorithms used in business to implement in realistic case stud- ies and project Know how to use tools for forecasting, analyzing and drawing con- clusions about business data Understand and apply machine learning to business forecasting, from which we can predict and draw conclusions about development directions and business plans

¢ Analyze the stock price of Apple from 2019 till 08 - 11 - 2023

— Define the fluctuation and research about the factors that affect the rise

or drop of the stock price in this period

¢ Forecast the stock price of Apple

Analysis methods:

¢ Analysing:

— Excel, R, Python, SPSS (we choose all 4 recommend languages and applications so we can know the pros and cons of each languages and applications)

— Plotting data and processing the data so it can be used for analyze and forecast models

— Perform static analysis to get the values of Mean, Median, Mode, Vari- ance, Standard Deviation, Range, and Standard Error of Mean, Skew- ness, and Kurtosis of the data

— Perform Z-Test, F-test, ANOVA to conclude about the dependance of stock price to other factors

¢ Forecasting: ARIMA model, LSTM model in Python language

3 RESEARCH METHODOLOGY

°® Secondary Research:

— Literature Review: Explore academic papers, industry reports, and books that analyze Apple’s business strategies, market performance, and tech- nological advancements

— Financial Reports and Filings: Access Apple’s annual reports, SEC fil- ings, and financial statements to understand its financial health, revenue sources, and strategic initiatives

— Industry Analysis: Review industry reports, market analyses, and com- petitor data to understand the technological landscape, market trends, and Apple’s competitive positioning

¢ Primary Research: Concepts and Classifications: Understanding basic con- cepts such as stocks, securities, dividends, investment funds, and various types of securities (stocks, bonds, ETFs, etc.)

Theory of Models and Functions: (ARIMA, LSTM) Stock Valuation Models: Studying stock valuation models such as dividend discount models, asset- based models, and forward-looking stock valuation models

Introduction to the Content of Relevant Documents:

— Apple’s Financial Reports: Examining Apple’s financial reports to un- derstand its financial health, revenue, and profit This is crucial for stock valuation and growth potential analysis

— Market Analysis Reports: Studying market reports and analyses, espe- cially within the technology industry and Apple’s business, to compare against competitors and industry trends

— Investment Philosophy Research: Exploring research on investment philoso- phies, how professional investors evaluate stocks, and effective invest- ment strategies

Data Analysis: Quantitative Analysis: Use statistical tools to analyze finan- cial data

¢ Online Resources and Press Releases: Monitor online sources, news articles, press releases, and Apple’s official communications for the latest updates, product launches, and strategic moves

Scenario Planning: Develop scenarios and projections for Apple’s future based on the analyzed data and market trends

4 THEORETICAL FRAMEWORK AND RELATED RE- PORTS

4.1 Models and Functions Theoretical Background

4.1.1 Descriptive Analysis

« Mean

— Mean is the ratio of the sum of all observations in the data to the total number of observations This is also known as average Thus, mean is a number around which the entire data set is spread

— This is the commonly used tool for measuring intervals and ratios

-> Mean in stock market: It is the average value of all stock prices in a dataset

It can provide an overall view of the average price of stocks

* Mode

Mode is the number that has the maximum frequency in the entire data set

In other words, mode is the number that appears the most often A data can have one or more than one mode

— If there is only one number that appears the most number of times, the data has one mode, and is called uni-modal

— If there are two numbers that appear equally frequently, the data has two modes, and is called bi-modal

— If there are more than two numbers that appear equally frequently, the data has more than two modes We call that multi-modal

— This is the commonly used tool for measuring Categorical (nominal) Mode is not affected by values at both ends of the distribution

* Median

Median is the point which divides the entire data into two equal halves One half of the data is less than the median and the other half is greater than the median Median is calculated by first arranging the data in either ascending

variance indicates that data points are spread widely and a small variance indicates that the data points are closer to the data set’s mean

Standard Deviation

Standard Deviation: It is the square root of the variance and is commonly used to assess the level of volatility in stock prices A large standard deviation may indicate significant fluctuations in stock prices

¢ Range

Range is the difference between the maximum value and the minimum value

in the data set It is given as:

Standard Error of Mean Standard error of the mean is a method used to evaluate the standard deviation of a sampling distribution Moreover, It is used to measure the difference in mean values of one sample from another under conditions of the same distribution

Skewness The measure of asymmetry in a probability distribution is defined

by skewness Skewness can either be positive, negative or undefined

— Positive Skew: This is the case when the tail on the right side of the curve is bigger than that on the left side For these distributions, the mean is greater than the mode

— Negative Skew: This is the case when the tail on the left side of the curve

is bigger than that on the right side For these distributions, the mean is smaller than the mode

¢ Kurtosis Kurtosis describes whether the data is light tailed (ack of outliers)

or heavy tailed (outliers present) when compared to a normal distribution There are three kinds of kurtosis:

— Mesokurtic: This is the case when the kurtosis is zero, similar to normal distributions

— Leptokurtic: This is when the tail of the distribution is heavy (outlier present) and kurtosis is higher than that of the normal distribution

— Platykurtic: This is when the tail of the distribution is light (no outlier) and kurtosis is lesser than that of the normal distribution

« ANOVA test

— ANOVA, or Analysis of Variance, is a statistical technique used to com- pare means between three or more groups to determine if there are sta- tistically significant differences among them It assesses whether the

means of different groups are equal or if at least one of the group means

is different from the others

— ANOVA examines the variance within different groups and compares it

to the variance between the groups The test calculates an F-statistic, which represents the ratio of between-group variance to within-group variance If the calculated F-statistic is sufficiently large and the asso- ciated p-value is below a chosen significance level (often 0.05), it in- dicates that there are significant differences between the group means There are different types of:

* One-Way ANOVA: Used when comparing the means of three or more independent (unrelated) groups to determine if there are sig- nificant differences among them

+ Two-Way ANOVA: Compares means across two independent vari- ables (factors) simultaneously to determine their individual and in- teractive effects on the dependent variable

4.1.2 ARIMA Model

1 What is Arima?

An autoregressive integrated moving average model is a form of regression analysis that gauges the strength of one dependent variable relative to other changing variables The model’s goal is to predict future securities or finan- cial market moves by examining the differences between values in the series instead of through actual values An ARIMA model can be understood by outlining each of its components as follows:

¢ Autoregression (AR): refers to a model that shows a changing variable that regresses on its own lagged, or prior, values

¢ Integrated (I): represents the differencing of raw observations to allow the time series to become stationary (i.e., data values are replaced by the difference between the data values and the previous values)

* Moving average (MA): incorporates the dependency between an obser- vation and a residual error from a moving average model applied to lagged observations

2 Arima model parameters

Each component in ARIMA functions as a parameter with a standard nota- tion For ARIMA models, a standard notation would be ARIMA with p, d, and q, where integer values substitute for the parameters to indicate the type

of ARIMA model used The parameters can be defined as:

° p: the number of lag observations in the model, also known as the lag order

¢ d: the number of times the raw observations are differenced; also known

as the degree of differencing

* q: the size of the moving average window, also known as the order of the moving average

3 How to build Arima model?

¢ Step 1: Data Analysis: Understand the time series data, identify trends, seasonality, and other patterns that might exist

* Step 2: Stationarity: Check if the data is stationary If not, apply dif- ferencing to make it stationary Use tools like the Augmented Dickey- Fuller (ADF) test to confirm stationarity

° Step 3: Model Identification: Identify the appropriate values of p, d, and

q for the ARIMA model

— p (AR): The number of lag observations included in the model Identify using the partial autocorrelation function (PACF) plot

— d (I): The number of differencing required Identify by checking stationarity or using the ADF test

— q (MA): The size of the moving average window Identify using the autocorrelation function (ACF) plot

* Step 4: Model Estimation: Once you’ve determined the model parame- ters (p, d, q), fit the ARIMA model to the data You’ll perform statistical estimation using techniques like maximum likelihood estimation

* Step 5: Model Evaluation: Validate the model using test data Calculate metrics like Mean Squared Error (MSE), Mean Absolute Error (MAE),

or Root Mean Squared Error (RMSE) to assess model performance

* Step 6: Forecasting: After validating the model, use it to forecast future data points

4.1.3 LSTM Model

4.2 LSTM[1][2]

Long Short Term Memory is a kind of recurrent neural network In RNN out- put from the last step is fed as input in the current step It tackled the problem of long-term dependencies of RNN in which the RNN cannot predict the word stored

in the long-term memory but can give more accurate predictions from the recent

information As the gap length increases RNN does not give an efficient perfor- mance LSTM can by default retain the information for a long period of time It is used for processing, predicting, and classifying on the basis of time-series data Long Short-Term Memory (LSTM) is a type of Recurrent Neural Network (RNN) that is specifically designed to handle sequential data, such as time series, speech, and text LSTM networks are capable of learning long-term dependen- cies in sequential data, which makes them well suited for tasks such as language translation, speech recognition, and time series forecasting

A traditional RNN has a single hidden state that is passed through time, which can make it difficult for the network to learn long-term dependencies LSTMs address this problem by introducing a memory cell, which is a container that can hold information for an extended period of time The memory cell is controlled by three gates: the input gate, the forget gate, and the output gate These gates decide what information to add to, remove from, and output from the memory cell

The input gate controls what information is added to the memory cell The forget gate controls what information is removed from the memory cell And the output gate controls what information is output from the memory cell This allows LSTM networks to selectively retain or discard information as it flows through the network, which allows them to learn long-term dependencies

LSTMs can be stacked to create deep LSTM networks, which can learn even more complex patterns in sequential data LSTMs can also be used in combination with other neural network architectures, such as Convolutional Neural Networks (CNNs) for image and video analysis

It explores the details to be removed from the block A sigmoid function decides

it It looks at the previous state (ht-1) and the content input (Xt) and outputs a number between O (ignore this) and 1 (keep this as it is) for each number in the cell state Ct- first

4.2.2 Input Gate:

It detects which value from the input should be used to modify the memory The Sigmoid function decides which values to pass 0 or 1 And the tanh function gives weights to the passed values, deciding their importance between -1 and 1

4.2.3 Output Gate:

The block’s input and memory are used to decide the output The Sigmoid function decides which values to pass 0 or 1 And the tanh function decides which values to pass 0, 1 And the tanh function gives weights to the passed values, deciding how important they are in the equation range from -1 to 1 and multiply with the output as sigmoid

¢ LSTM enables the model to capture and remember the important context, even when there is a significant time gap between relevant events in the se- quence So where understanding context is important, LSTMS are used eg machine translation

4.2.5 Disadvantages of LSTM

* Compared to simpler architectures like feed-forward neural networks LSTM networks are computationally more expensive This can limit their scalability for large-scale datasets or constrained environments

* Training LSTM networks can be more time-consuming compared to simpler models due to their computational complexity So training LSTMs often re- quires more data and longer training times to achieve high performance

¢ Since it is processed word by word in a sequential manner, it is hard to paral- lelize the work of processing the sentences

5 COMPANY INTRODUCTION

5.1 Overview of Apple

Introduction Apple Inc is an American multinational technology company headquartered in Cupertino, California As of March 2023, Apple is the world’s biggest company by market capitalization, and with US$394.3 billion the largest technology company by 2022 revenue As of June 2022, Apple is the fourth-largest personal computer vendor by unit sales; the largest manufacturing company by rev- enue; and the second-largest mobile phone manufacturer in the world It is consid- ered one of the Big Five American information technology companies, alongside Alphabet (parent company of Google), Amazon, Meta, and Microsoft

Apple was founded as Apple Computer Company on April 1, 1976, by Steve Wozniak, Steve Jobs, and Ronald Wayne to develop and sell Wozniak’s Apple I personal computer It was incorporated by Jobs and Wozniak as Apple Computer, Inc in 1977

Apple became the first publicly traded U.S company to be valued at over $1 trillion in August 2018, then at $2 trillion in August 2020, and at $3 trillion in January 2022 In June 2023, it was valued at just over $3 trillion

Apple’s core values include: Accessibility

Business field - Business model

Apple is known for its diversification across multiple business segments, contribut- ing to a wide range of revenue streams(Figure 1) The company operates in areas such as consumer electronics, software development, digital services, and more This diversification strategy allows Apple to mitigate risks associated with depen- dence on a single product or market, fostering stability and resilience in the face

of changing market dynamics By engaging in a multitude of sectors, Apple not only enhances its financial performance but also maintains a strong position in the global technology landscape

How to Analyze an Income Statement

mua “a Wi @£conomyApp & PP ECONOMY INSIGHTS

Figure 1: Apple’s Business Model[3]

Apple Apple Inc (Apple) designs, manufactures, and markets smartphones, tablets, personal computers, and wearable devices The company offers software applications and related services, accessories, and third-party digital content Ap- ple’s product portfolio includes iPhone, iPad, Mac, iPod, Apple Watch, and Apple

TV It also provides advertising services, payment services, cloud services, and various consumer and professional software applications such as iOS, macOS, iPa- dOS, and watchOS, iCloud, AppleCare, and Apple Pay Apple sells and deliv- ers digital content and applications through the App Store, Apple Arcade, Apple News+, Apple Fitness+, Apple Card, Apple TV+, and Apple Music The com- pany’s business operations span the Americas, Europe, the Middle East, Africa, and Asia-Pacific Apple is headquartered in Cupertino, California, the US

iPhone Services @ Wearables, Home and Accestories @ Mac ®4Ped @ Other Product:

Figure 2: Apples’s Business Revenue By Source[4]

Apple primarily reports revenue on a geographical basis, specifically the Amer- icas (North and South America), Europe (European countries, India, Middle East and Africa), China, Hong Kong, Taiwan, Japan and Rest of Asia Pacific (Australia and other Asian countries) In fiscal 2020, the Americas, Europe, China, Japan and Rest of Asia-Pacific accounted for 45.4%, 25%, 14.7%, 7.8%, and 7.1% of total revenue, respectively

By country

Figure 3: Apples’s Business Revenue By Country[4]

5.2 Apple Stock Review

Apple’s position in S&P500 !

Figure 4: The proportion of Apple in the S&P 500 index

FAANG is the collective term for the world’s five major tech giants: Facebook (now Meta), Amazon, Apple, Netflix, and Alphabet However, in recent years, due

to the decline of Netflix, Microsoft has replaced Netflix in the group As a result, some people refer to it as FAAMG or MAMAA (with Facebook renamed Meta and Google’s parent company as Alphabet)

Currently, these two stocks account for 7.11% and 6.14% of the S&P 500, re- spectively Both of them experienced significant declines in 2022, but they re- bounded in 2023 Apple surged by 21%, while Microsoft saw an increase of 14%

'Wikipedia, "S&P 500"

—Apple —Alphabet Meta ==Microsof( -—-Amazon —Netflix 200%

Figure 5: The rate of return on the stocks of major U.S technology companies

As of the first quarter of 2023, Apple shares still account for the largest profit margin, surpassing all other giants in the industry

6 DATASET AND DEPLOYMENT

6.1 Introduction to the collected dataset

6.1.1 Dataset 1

In this report, we utilized a dataset pertaining to the stock prices of Apple Inc The dataset was collected from the Yahoo Finance website The data set compiled

by our team includes information on the date and closing prices for each day over

a span of 5 years (from January 1, 2019, to November 8, 2023):

Our team utilized Data Set 1 for Descriptive Analysis and forecasting, employing both ARIMA and LSTM models

1 Date Close Inflation USDollarlndexClose FEDrate CPI UNRATE

* Inflation: US Inflation rate?

Description: The inflation rate is the percentage change in the price of prod- ucts and services from one year to the next (year over year)

While the United States has experienced a relatively low and stable inflation rate since the 1980s, inflation hit record highs in 2021 and 2022 in the wake

of the pandemic The annual inflation rate was 7.0% in December 2021 and 6.5% at the end of 2022 And now the inflation rate is 3.5%

* US Dollar Index Close?

US Dollar Index Close: collected from Investing.com (U.S Dollar Index (USDX) extracted from the ’Close’ column)

Description: The U.S dollar index (USDX) is a measure of the value of the U.S dollar relative to a basket of foreign currencies The USDX was estab- lished by the U.S Federal Reserve in 1973 The index is currently calculated

by factoring in the exchange rates of six foreign currencies, which include the euro (EUR), Japanese yen (JPY), Canadian dollar (CAD), British pound (GBP), Swedish krona (SEK), and Swiss franc (CHF)

FED rate (Federal Funds Rate): Collected from Investing.comf The term federal funds rate refers to the target interest rate range set by the Federal Open Market Committee (FOMC) This target is the rate at which commer- cial banks borrow and lend their excess reserves to each other overnight The federal funds rate is one of the most important interest rates in the U.S econ- omy That’s because it impacts monetary and financial conditions, which

in turn have a bearing on critical aspects of the broader economy including employment, growth, and inflation

* CPI (Consumer Price Index)*: Collected from U.S BUREAU OF LABORS STATISTICS

The term federal funds rate refers to the target interest rate range set by the Federal Open Market Committee (FOMC) This target is the rate at which commercial banks borrow and lend their excess reserves to each other overnight The federal funds rate is one of the most important interest rates in the U.S economy That’s because it impacts monetary and financial conditions, which

in turn have a bearing on critical aspects of the broader economy including employment, growth, and inflation

Unemployment Rate® The unemployment rate is the percentage of the labor force without a job It is a lagging indicator, meaning that it generally rises or falls in the wake of changing economic conditions, rather than anticipating them When the economy is in poor shape and jobs are scarce, the unem- ployment rate can be expected to rise When the economy grows at a healthy rate and jobs are relatively plentiful, it can be expected to fall The U.S un- employment rate is released on the first Friday of every month (with a few exceptions) for the preceding month

7 APPLE STOCK PRICE ANALYSIS FROM 2019 TO

2023

7.1.1 Mean, Median, Mode, Variance, Standard Deviation, Range, Quartiles, Stan-

dard Error of Mean, Skewness, and Kurtosis of Close Price

1 Excel

a Multiple modes exist

The smallest value is shown

Figure 7: Result of SPSS 2019

‹ 2020

© Comments Add-ins Add-ins Analyze Data

Statistics close

a Multiple modes exist

The smallest value is shown

Figure 8: Result of SPSS 2020

¢ 2021 Statistics

a Multiple modes exist

The smallest value is shown

Figure 9: Result of SPSS 2021

© 2022

Statistics Close

1 163.759995

2 175.839996

or Name: Close, dtype: float64

Standard Deviation: 45.679123385791506 Variance: 2086.5823132943647 Range: 160.90249599999999 SEM: 1.306184519669035 Skewness: -@.41133636690171194 Kurtosis: -1.1776655078461

Figure 12: Result of Python 2019-2023

1 Excel

Figure 14: ANOVA - Regression - Result of Excel

2 SPSS Due to some problem technical, our result of SPSS ANOVA is quite different from the other tools

a Dependent Variable: Close

b Predictors: (Constant), UNRATE, USDollarindexClose, Inflation, FEDrate, CPI

€ apple_month.ipynb Tệp Chỉnhsửa Xem Chèn Thời gianchạy Côngcụ Trợgiúp Chỉnh sửa lần gần đây nhất vào 14 tháng 11

Or Model: OLS Adj R-squared: 9.615

7.2.1 Mean, Median, Max, Min

Mean Median Maximum Minimum

Figure 17: Mean, Median, Max, Min of Close Price a) Data Analysis

¢ The mean close price for Apple stocks has been steadily increasing over the years, rising from approximately $50.79 in 2019 to $169.39 in 2023, indicat- ing a consistent upward trend in Apple stock prices

¢ Similarly, the median close price for Apple Stock has also exhibited a steady increase over the years, further emphasizing the upward trend in Apple stocks

¢ There was rapid growth from 2019 to 2020, with the average price nearly

doubling from $50 to almost $100

b) Compare with financial statement results and reality events

* Efficient Business Operations: Based on the financial reports and business results of Apple, it can be observed that Apple has been operating effectively over the past 5 years Revenue, net income, and profit margin have consis- tently grown from 2019 to 2023 This is also the reason why investors choose

to buy AAPL stocks, leading to a continuous upward trend in the stock price (Close)

400B 300B 200B 100B

mRevenue #8 Netincome gs Profit Margin

Figure 18: Chart Displaying Revenue, Net Income, and Profit Margin Percentage for Apple (2019-2023)

- COVID-19 Pandemic and its Impact on Apple: Amid the pandemic, Apple stands out as the only smartphone brand equipped with an ecosystem

of services to anticipate user needs

Continuous Innovation and the Launch of New Products: The onset of the

COVID-19 pandemic in 2019 had relatively minimal impact on the United States but did affect Apple’s consumer product markets, including China Despite office closures from mid-March 2020, Apple continued to release

a series of products since the onset of the Covid-19 pandemic In 2019, the iPhone 11 emerged as the best-selling product in Q1, followed by the iPhone Pro Max and iPhone XR The 11 Pro did not make it to the top three Apple’s sales figures were least affected by COVID-19 in 2019, showcasing the strength of the Apple brand