Algorithmic Trading Model with ML4T Chapter 1 Storage Benchmark Examples

NOTE: This script is for learning purposes only and does not constitute a recommendation for buying or selling any stock mentioned in this script.

SUMMARY: This project aims to construct and test an algorithmic trading model and document the end-to-end steps using a template.

INTRODUCTION: This script aims to replicate the examples found in chapter one of the book Machine Learning for Algorithmic Trading by Stefan Jansen. The script seeks to validate further the Python environment and package requirements for running these code examples. The eventual goal is to integrate various example code segments into an end-to-end algorithmic trading system.

This benchmarking exercise used the Google Colab environment as it has the prerequisite libraries and packages already built-in.

Dataset ML Model: Time series analysis with numerical attributes

Dataset Used: Programmatically generated DataFrame with random data

Source and Further Discussion of the Code Examples: https://www.ml4trading.io/chapter/1

The HTML formatted report can be found here on GitHub.

Algorithmic Trading Model with ML4T Chapter 1 SEC’s EDGAR Filing Examples

NOTE: This script is for learning purposes only and does not constitute a recommendation for buying or selling any stock mentioned in this script.

SUMMARY: This project aims to construct and test an algorithmic trading model and document the end-to-end steps using a template.

INTRODUCTION: This script aims to replicate the examples found in chapter one of the book Machine Learning for Algorithmic Trading by Stefan Jansen. The script seeks to validate further the Python environment and package requirements for running these code examples. The eventual goal is to integrate various example code segments into an end-to-end algorithmic trading system.

Dataset ML Model: Time series analysis with numerical attributes

Dataset Used: US Public Company Filing Hosted by SEC’s EDGAR Service

Source and Further Discussion of the Code Examples: https://www.ml4trading.io/chapter/1

The HTML formatted report can be found here on GitHub.

Algorithmic Trading Model with ML4T Chapter 1 ‘yfinance’ Market and Fundamental Data Examples

NOTE: This script is for learning purposes only and does not constitute a recommendation for buying or selling any stock mentioned in this script.

SUMMARY: This project aims to construct and test an algorithmic trading model and document the end-to-end steps using a template.

INTRODUCTION: This script aims to replicate the examples found in chapter one of the book Machine Learning for Algorithmic Trading by Stefan Jansen. The script seeks to validate further the Python environment and package requirements for running these code examples. The eventual goal is to integrate various example code segments into an end-to-end algorithmic trading system.

Dataset ML Model: Time series analysis with numerical attributes

Dataset Used: US Equities and Fund Prices Hosted by Yahoo! Finance

Source and Further Discussion of the Code Examples: https://www.ml4trading.io/chapter/1

The HTML formatted report can be found here on GitHub.

Algorithmic Trading Model with ML4T Chapter 1 Pandas Data Reader Examples

NOTE: This script is for learning purposes only and does not constitute a recommendation for buying or selling any stock mentioned in this script.

SUMMARY: This project aims to construct and test an algorithmic trading model and document the end-to-end steps using a template.

INTRODUCTION: This script aims to replicate the examples found in chapter one of the book Machine Learning for Algorithmic Trading by Stefan Jansen. The script seeks to validate further the Python environment and package requirements for running these code examples. The eventual goal is to integrate various example code segments into an end-to-end algorithmic trading system.

Dataset ML Model: Time series analysis with numerical attributes

Dataset Used: US Equities and Fund Prices Hosted by Various Data Sources

Source and Further Discussion of the Code Examples: https://www.ml4trading.io/chapter/1

The HTML formatted report can be found here on GitHub.

Erika Andersen on Be Bad First, Part 5

In the book, Be Bad First: Get Good at Things Fast to Stay Ready for the Future, Erika Andersen shares her mindset and techniques for learning new things well and quickly.

These are some of my favorite concepts and takeaways from reading the book.

Chapter 5: Neutral Self-Awareness: The American Idol Syndrome

In this chapter, Erika Andersen discusses how a lack of neutral self-awareness can inhibit our ability to be open to learning. She offers the following observations and recommendations for us to think about:

Most of us have an inflated sense of our capabilities when assessing ourselves. We do not want to acknowledge our deficits because we secretly believe we cannot do anything about them.

There is a surprisingly simple way to become aware of how we see ourselves and shift our self-perception if it is inaccurate. We can become more neutrally self-aware by:

  • Managing our self-talk,
  • Becoming our fair witness, and
  • Inviting good “sources.”

People who see themselves objectively start by learning to manage how they talk about themselves. We all have a continuous mental monologue running at the back of our minds. But moreover, we change the content of that mental monologue.

Recognizing what we are saying inside our heads is the first step to having more control over it. Furthermore, having the ability to shift those inaccurate, unhelpful, unsupportive voices to be more accurate, neutral, and supportive is a powerful capability.

The steps involved in managing our self-talk include:

  • Recognize: The first step is to “hear” it.
  • Record: Write down our self-talk and narratives.
  • Rethink: Decide how to revise it to be more accurate and helpful.
  • Repeat: Managing our self-talk requires repetition.

Becoming a fair witness (FW) means being as objective and accurate as possible. When someone acts in the FW capacity, she speaks only from her direct experience. The FW role cannot indulge in speculation, cherry-pick the data, say what she hopes is true, or avoid looking at what she does not want to be true. The FW is proscribed from doing everything we generally do when thinking about ourselves.

The steps in becoming our own fair witness include:

  • Recognize and record our self-talk about our strengths and weaknesses in an area where we want to level up.
  • Ask ourselves, Is my self-talk accurate?
  • If we are unsure, ask, What facts do I have about myself in this area?
  • Rethink our self-talk to be more accurate and objective.

Incredibly self-aware people sometimes cannot see themselves entire clearly. For those occasions, we need feedback from external sources. A good “source” should include three equally essential elements:

  • See you clearly
  • Want the best for you
  • Are willing to be honest

Aspiration provides the fuel that will move us forward into new learning. Neutral self-awareness allows us to see where we are on the journey.

數據、信息和決策

(從我一個尊敬的作家,賽斯·高汀

數據無處不在,但將其轉化為信息並不是免費的。

這需要專注、努力、諮詢和時間。

更多信息只有在幫助您做出決定時才有用。 知道土星的溫度是沒有用的,更準確地了解它的用處不大。那是因為我們沒有做出任何涉及另一個星球溫度的決定。

我們被電子表格、網絡或群組似乎希望我們了解的數據所包圍。昨天有多少人點擊了,或者有人在評論中寫了什麼,一本後備書的銷量,或者那家商店與這家商店的客流量。

但是,如果您不打算使用數據做出決定,請不要花時間將自己暴露在其中。這是工作中的阻力。

如果你不能對數據做出任何事情,它就永遠不會成為信息。

Multi-Class Image Classification Model for Belgium Traffic Sign Using TensorFlow Take 5

Template Credit: Adapted from a template made available by Dr. Jason Brownlee of Machine Learning Mastery.

SUMMARY: This project aims to construct a predictive model using a TensorFlow convolutional neural network (CNN) and document the end-to-end steps using a template. The Belgium Traffic Sign dataset is a multi-class classification situation where we attempt to predict one of several (more than two) possible outcomes.

INTRODUCTION: This dataset contains over 7,200 images of 62 varieties of traffic signs used in Belgium. The researcher performed experiments on the dataset to create a CNN-based classification system.

ANALYSIS: The EfficientNetV2S model’s performance achieved an accuracy score of 99.41% after 10 epochs using the training dataset. When we applied the model to the validation dataset, the model achieved an accuracy score of 94.05%.

CONCLUSION: In this iteration, the TensorFlow EfficientNetV2S CNN model appeared suitable for modeling this dataset.

Dataset ML Model: Multi-Class classification with numerical features

Dataset Used: Belgium_Traffic_Sign_image_data_62_class_data

Dataset Reference: https://www.kaggle.com/datasets/abhi8923shriv/belgium-ts

One source of potential performance benchmarks: https://www.kaggle.com/datasets/abhi8923shriv/belgium-ts/code

The HTML formatted report can be found here on GitHub.

Multi-Class Image Classification Model for Belgium Traffic Sign Using TensorFlow Take 4

Template Credit: Adapted from a template made available by Dr. Jason Brownlee of Machine Learning Mastery.

SUMMARY: This project aims to construct a predictive model using a TensorFlow convolutional neural network (CNN) and document the end-to-end steps using a template. The Belgium Traffic Sign dataset is a multi-class classification situation where we attempt to predict one of several (more than two) possible outcomes.

INTRODUCTION: This dataset contains over 7,200 images of 62 varieties of traffic signs used in Belgium. The researcher performed experiments on the dataset to create a CNN-based classification system.

ANALYSIS: The VGG19 model’s performance achieved an accuracy score of 98.93% after 10 epochs using the training dataset. When we applied the model to the validation dataset, the model achieved an accuracy score of 93.85%.

CONCLUSION: In this iteration, the TensorFlow VGG19 CNN model appeared suitable for modeling this dataset.

Dataset ML Model: Multi-Class classification with numerical features

Dataset Used: Belgium_Traffic_Sign_image_data_62_class_data

Dataset Reference: https://www.kaggle.com/datasets/abhi8923shriv/belgium-ts

One source of potential performance benchmarks: https://www.kaggle.com/datasets/abhi8923shriv/belgium-ts/code

The HTML formatted report can be found here on GitHub.