OWL Magazine Korea
Learn More

“Mystical ChatGPT Utilization” by Hong Chang-soo

February 12, 2024 719 Views

After the outbreak of COVID-19, the world has undergone rapid changes, with new technologies emerging. Blockchain technology, represented by Bitcoin, has been introduced, attracting attention and leading many people to invest in cryptocurrencies. Similarly, “NFT,” utilizing blockchain technology, has gained popularity. Moreover, the “metaverse” technology, unfolding the “online” world, has also been noticed.

However, these once-prominent technologies have somewhat faltered. “NFT” vanished like a mirage, and cryptocurrencies, along with the “Luna-Terra” coin incident, suffered a significant decline. The same fate befell the metaverse as the COVID-19 situation waned, gradually losing people’s interest. Of course, in the case of the metaverse, development continues through Meta’s Oculus, with Apple planning to launch “Vision Pro” soon, so the outcome remains uncertain.

“The Emergence of Chat GPT, AI Technology”

The field of “AI” has made a significant impact on society since the unveiling of “Chat GPT” on November 30, 2022, shocking many people.

It introduced a new dimension of “artificial intelligence technology,” initially approached with mere curiosity, but after using “Chat GPT,” one could instinctively recognize the emergence of AI that might surpass humans. Chat GPT caused a sensation from its release, surpassing 100 million monthly users in just two months, overwhelmingly faster compared to previous records. Instagram took 30 months and TikTok took 9 months to reach this milestone, while Chat GPT took only 2 months.

However, even after Chat GPT, Meta’s release of “Thread” surpassed 100 million monthly users in just five days, breaking records, but the impact brought by Chat GPT was substantial.

“Chat GPT: Integrating Humanities and Sciences”

The author introduces Chat GPT as a “hybrid talent in humanities and sciences,” explaining how it can aid in tasks related to writing, editing, and translation for humanities graduates, as well as being useful in fields like science, programming, coding, and statistics for engineering graduates. It’s truly a talent that bridges the humanities and sciences.

“Users of Artificial Intelligence: Those Who Utilize and Those Who Don’t”

After using artificial intelligence like Chat GPT for the first time, the author realizes that society will be divided into those who actively and effectively use AI and those who don’t. The author further categorizes talent into three tiers: AI development, AI utilization, and AI non-utilization.

“Utilizing Chat GPT Effectively”

The book explores various effective ways to utilize Chat GPT, including writing, creating outlines for books, paraphrasing, translation, content creation for blogs and YouTube, business proposals, and even learning programming languages. The author emphasizes the importance of asking good questions to obtain valuable answers from Chat GPT.

“Using Chat GPT for Data Analysis”

The author suggests that Chat GPT can be effectively used for data analysis, including applications in quantitative analysis and trading methods in stock trading based on data analysis.

“Receiving Career Coaching from Chat GPT”

In addition to translation and coding assistance, Chat GPT can help with writing resumes, cover letters, and preparing for job interviews, reflecting how artificial intelligence is becoming integrated into various aspects of society, including recruitment processes.

“Vulnerabilities in Chat GPT Regarding Security Issues”

The latter part of the book discusses potential issues with using Chat GPT, such as copyright problems with creations made using Chat GPT and security concerns since it is connected online.

“Using Chat GPT Smartly: Asking the Right Questions”

Ultimately, to obtain valuable answers from Chat GPT, one must ask good questions, emphasizing the importance of developing skills in asking insightful questions in the future world where such abilities will be increasingly valuable.

“Introduction to Python”

  1. Explain the types of data structures in Python and provide code examples.
  2. Explain Python’s basic syntax rules such as indentation, comments, and variable naming conventions.
  3. Explain what lists are in Python and provide list code examples.
  4. Explain what tuples are in Python and provide tuple code examples.
  5. Explain what sets are in Python and provide set code examples.
  6. Explain what dictionaries are in Python and provide dictionary code examples.
  7. Explain if statements in Python and provide code examples.
  8. Explain if-else statements in Python and provide code examples.
  9. Explain if-elif-else statements in Python and provide code examples.
  10. Explain while loops in Python and provide code examples.
  11. Explain for loops in Python and provide code examples.
  12. Provide example code for input and output in Python.
  13. Explain Python functions and provide code examples.
  14. Explain Python built-in functions and provide code examples.
  15. Explain major Python libraries, usage, and provide example code related to their usage.

“Foundations of Data Science: Basic Statistics and Data Analysis”

  1. Explain the data analysis process and provide simple Python example code.
  2. Explain how to use Jupyter for Python usage.
  3. Explain how to use Google Colab for Python usage.
  4. Explain basic usage of NumPy in Python and provide example code.
  5. Explain indexing and slicing in NumPy, basic usage of Pandas, and provide example code.
  6. Explain how to create a DataFrame using exam scores in Pandas.
  7. Explain how to import Excel files using Pandas in Python.
  8. Explain input/output functions in Pandas.
  9. Explain loc and iloc for data extraction in Pandas, and provide examples.
  10. Explain matplotlib and seaborn for data visualization and provide example code.
  11. Explain concat, merge, and join functions for data merging in Python and provide example code.
  12. Explain groupby function for data aggregation in Pandas and provide example code.
  13. Explain descriptive statistics functions in Pandas and provide example code.
  14. Explain head, tail, shape, info, and describe functions for data exploration in Pandas.
  15. Explain descriptive statistics, inferential statistics, and statistical hypothesis testing in Python and provide examples.
  16. Explain correlation analysis in Python and provide example code.
  17. Explain regression analysis in Python and provide example code.
  18. Explain multiple regression analysis in Python and provide example code.
  19. Explain variance inflation factor (VIF) for diagnosing multicollinearity in Python and provide example code.

“Data Science: Artificial Intelligence, Machine Learning, Deep Learning”

  1. Show the procedure of machine learning analysis in Python and explain the types of machine learning.
  2. Show an example of machine learning analysis using the iris dataset from the Python scikit-learn library.
  3. Explain the method of splitting data for machine learning analysis.
  4. Explain the concept of Support Vector Machine (SVM) in machine learning and provide example code.
  5. Describe the types of deep learning and provide basic code.
  6. Explain how to use TensorFlow for deep learning applications.
  7. Describe the concept of Activation Functions in deep learning and explain the types.
  8. Explain early stopping, regularization, and dropout techniques for addressing overfitting in deep learning.
  9. Describe Convolutional Neural Networks (CNN) and provide a Python example code.
  10. Explain Recurrent Neural Networks (RNN) and provide a Python example code.
  11. Describe Long Short-Term Memory (LSTM) and provide a Python example code.
  12. Explain Generative AI and provide detailed information about the Transformer.
  13. Explain NLTK for natural language processing and provide example code.
  14. Provide executable code for logistic regression using the German Credit Data.

“Introduction to R Language”

  1. Explain the R language and its characteristics.
  2. Describe the application areas of the R language.
  3. Explain the installation process of the R language.
  4. Describe the application areas of the R language.
  5. Explain the installation process of the R language.
  6. Describe the main screens and features of RStudio.
  7. Explain the main shortcuts of RStudio.
  8. Explain the basic concepts of R’s data types and provide code examples.
  9. Explain the basic concepts of R’s data structures and provide code examples.
  10. Explain the concept of data frames in R and provide code examples.
  11. Explain variables in R and provide example code.
  12. Explain functions in R and provide example code.
  13. Explain packages in R and how to use them.
  14. Explain the types of operators in R and provide example code.
  15. Explain concepts of importing and exporting data in R and provide example code.
  16. Explain the main functions and usage examples for checking datasets in R.
  17. Explain the main functions and usage examples for manipulating data in R
  18. Explain the main functions and usage examples for computing data in R.
  19. Explain the main functions and usage examples for plotting graphs in R.
  20. Explain the concept of conditionals in R and provide example code.
  21. Explain the concept of loops in R and provide example code.
  22. Explain the concept of the dplyr package for data manipulation in R and provide example code for its main functions.
  23. Explain the concept of ggplot2 in R and provide usage examples.

“SQL”

  1. Explain the concept and characteristics of Relational Database Management Systems (RDBMS).
  2. Describe products that utilize relational databases.
  3. Explain SQL and introduce its types.
  4. Provide SQL commands to inspect the structure of a database.
  5. Describe key SQL statements used for data manipulation.
  6. Explain how to create tables in SQL and provide examples.
  7. Provide commands and examples for data insertion and deletion in SQL.
  8. Explain the basic syntax of the SELECT statement used for data retrieval in SQL.
  9. Describe how to specify query conditions using the WHERE clause in SQL’s SELECT statement.
  10. Explain how to use the FROM, WHERE, and ORDER BY clauses simultaneously in SQL’s SELECT statement.
  11. Describe how to retrieve data using condition operators, LIKE operator, IN operator, and BETWEEN operator in SQL’s SELECT statement.
  12. Provide examples of using DISTINCT for duplicate removal in SQL.
  13. Explain SQL operators and major SQL functions, providing example code.
  14. Explain the CASE expression in SQL.
  15. Describe the GROUP BY clause and aggregation functions used for data aggregation in SQL.
  16. Explain JOIN for establishing relationships between tables in SQL and provide example code.
  17. Describe the UNION clause for retrieving data from multiple tables without joining them in SQL and provide example code.
  18. Provide example code utilizing subqueries in SQL.
  19. Create a sample SQL example table and provide a learning prompt with example data to practice SQL queries.
  20. Present multiple-choice quizzes for SQL coding practice, with explanations for correct answers.
  21. Optimize the following SQL query: [Insert SQL query here]

“VBA”

  1. Explain what VBA is and what it can do.
  2. Describe the basic interface of the Excel VBA editor.
  3. List frequently used menus in the Excel VBA editor.
  4. Provide code and explanations for VBA’s basic syntax.
  5. Explain Sub procedures and Function procedures in VBA, providing example code.
  6. Describe conditional statements in VBA and provide code examples.
  7. Explain loop structures in VBA and provide code examples.
  8. Introduce built-in functions in VBA.
  9. Explain Dialog Control Language in VBA and provide example code.
  10. Provide code to calculate the average closing price of Samsung Electronics using VBA.
  11. Convert the following function into Excel VBA code: [Insert function here]
  12. Explain how to create Excel VBA example code and create macros step by step.

“Financial Data Analysis”

  1. Identify industries and items for successful investment in the securities market within the next 10 years.
  2. Explain what Quantitative Investing is and describe its types.
  3. Explain how to utilize ChatGPT in Quantitative Investing.
  4. Describe the types of trend-following trading and provide related Python code.
  5. Provide Python code and graphs for a moving average crossover strategy on Samsung Electronics from January 1, 2020, to April 30, 2023, using FinanceDataReader.
  6. Provide Python code and graphs for MACD analysis on Samsung Electronics from January 1, 2020, to April 30, 2023, using FinanceDataReader.
  7. Provide Python code and graphs for an LSTM neural network prediction model on Samsung Electronics from January 1, 2020, to April 30, 2023, using FinanceDataReader.
  8. Provide Python code to download and graph VX data from January 1, 2020, to April 30, 2023, using FinanceDataReader.
  9. Provide Python code to download Bitcoin data from January 1, 2010, to April 30, 2023, using FinanceDataReader and plot the graph.
  10. Provide Python code to perform Granger Causality test on the daily returns of Samsung Electronics and KOSPI from January 1, 2020, to April 30, 2023, using FinanceDataReader.
  11. Provide Python code to implement a channel breakout strategy on Tesla from January 1, 2020, to April 30, 2023, using yfinance and plot the graph.
  12. Provide Python code to download and graph WT (Crude Oil) from January 1, 2020, to April 30, 2023, using pandas_datareader.
  13. Explain the Sharpe Ratio for evaluating performance in Quantitative Investing and provide Python example code.
  14. Provide Python code for calculating the Risk Parity Portfolio in Quantitative Investing.
  15. Explain Maximum Drawdown (MDD) in Quantitative Investing and provide Python example code.
  16. Provide Python code for calculating autocall structured products in Quantitative Investing.
  17. Provide Python code for calculating discounted cash flow (DCF) for enterprise valuation.
  18. Explain Earnings Per Share (EPS) and provide Python example code for calculating EPS.
  19. Explain Price to Book Ratio (PBR) and provide Python example code for PBR.
  20. Provide Python example code using the QuantLib library to calculate prices for various financial products.
  21. Explain the Black-Litterman model for asset allocation and provide Python example code.

I think I need to take more interest in programming and engineering fields. While reading books, the most common thought I had was that I should have more interest in programming and engineering. Since switching my major to humanities, I haven’t studied programming. However, as the era of AI has already arrived, I realized that I should study programming and engineering at least a bit before it’s too late.

Nowadays, people don’t necessarily need to code from start to finish as in the past. However, I believe that at least having a basic understanding is necessary, even if it’s just to utilize AI technology like ChatGPT. Knowing the basics allows one to think about how to combine things effectively.

“Fastest way to become a data analysis expert using the magic of ChatGPT”

Tags: