brief introduction
Artificial intelligence is in the ascendant, and machine learning algorithms, as one of the most important technologies for realizing artificial intelligence, have aroused the interest of countless relevant practitioners. This book introduces the theoretical basis and advanced practical cases of machine learning algorithms in detail. The theoretical part introduces the path to build a machine learning project system, including business scenario disassembly, feature engineering, model evaluation and selection, and model optimization; the practical part introduces the industry Common business scenarios include computational advertising, supply and demand forecasting, intelligent marketing, and dynamic pricing. The source code of all cases is included with the book. Please see the back cover for how to obtain it.
The content of this book is explained in simple terms and combines theory with practice to help fresh computer graduates, cross-professional practitioners, algorithm engineers and other readers to build a machine learning project implementation process from scratch, quickly master key technologies, and quickly grow from a novice to a unique algorithm engineer.
About the Author
Wang Congying holds a master's degree from the School of Computer Science at Beijing University of Posts and Telecommunications (National Demonstration Software School). She is currently a senior algorithm engineer for Didi's internationalization and is responsible for Didi's international growth and scheduling algorithm strategies. He has worked for many well-known domestic and foreign technology companies such as Kuaishou, SF Express, and VMware. From 0-1 to 1-10, he participated in the design and led the development of multiple projects in which machine learning algorithms empower business scenarios and significantly improve business results. Won silver and bronze medals in Kaggle competitions.
Xie Zhihui, Ph.D. from the University of Texas at Austin, has profound practical and theoretical experience in the fields of artificial intelligence and machine learning. He has worked for Internet platforms such as Didi Chuxing and Alibaba, and successfully built an industrial-level analysis and automated model platform, which played a key role in supporting business scale and rapid iteration. The author also worked as an advertising scientist at the Sunnyvale headquarters of Yahoo!, where he was engaged in research on Yahoo’s global display advertising and video advertising transactions and auction pricing mechanisms, contributing tens of millions of dollars in seller income. He taught at the University of Illinois before entering industry. The author has published more than ten papers in international conferences and magazines in related fields, and has more than twenty US patents pending/authorized.
Preface
The beginning of 2023 is a milestone and important stage for the explosion of artificial intelligence. When I completed the first draft of this book, large models represented by GPT developed by OpenAI were becoming popular. The ChatGPT model in the NLP field was very popular and triggered a heated discussion among the people. The latest update of GPT-4 has achieved a leap forward in large-scale multi-modal models. It can accept image and text input at the same time and output correct text responses. On the one hand, many colleagues engaged in artificial intelligence are amazed by the excellent performance of GPT-4, but on the other hand, they are also worried about their careers. If the large model of "big computing power + strong algorithm" is the future development trend of artificial intelligence, then are traditional machine learning algorithms still useful in real business scenarios? Will it be replaced by large models sooner or later? I don't think so. Every business scenario has its own uniqueness. The most valuable thing about an excellent algorithm engineer is a thorough understanding and long-term accumulation of business knowledge. Business knowledge is like the roots of the big tree of machine learning projects, theoretical knowledge is like the branches of the big tree, and algorithm applications are like the leaves on the branches. Only when the roots are deep enough can this big tree branch out. Loose leaves, flowers and fruits. So far, large models have not yet reached the level of human algorithm engineers in understanding and thinking about ever-changing, complex and diverse business forms. Even if one day we can develop algorithm applications for various business scenarios based on large models, it will still be difficult to understand and think about rapidly changing, complex and diverse business forms. Algorithm engineers are required to have strong business capabilities and solid theoretical knowledge of machine learning to guide large models to effectively learn specific business scenarios.
Machine learning practitioners in the era of explosive growth of artificial intelligence are undoubtedly lucky. How to better integrate artificial intelligence into all aspects of human life is an important issue to be solved in this era. Although this book does not cover complex model knowledge and business scenarios, it remains true to its roots. No matter how complex the model is, it is not fabricated out of thin air, but is made up of simple basic knowledge. Therefore, I hope that after reading this book, readers can establish a solid foundation of machine learning algorithms and a systematic way of thinking, and quickly master the new knowledge and new businesses that are rapidly iterating in the field of artificial intelligence.
The origin of this book In March 2022, editor Li Xiaobo from the Machinery Industry Press came to me and asked me if I could publish a book on the application of machine learning algorithms. This is my fifth year of working on the Internet. During this time, I have participated in the design and led the development of multiple projects in which machine learning algorithms empower business scenarios and significantly improve business results. I have also led many fresh graduates and interns. I found that many newcomers often memorize high-level model theories very well when they first enter the industry, but they cannot figure out the way and grasp the key points when they are actually applied. As a result, good steel is not used on the cutting edge and actual business benefits cannot be obtained. . It would be great if there was a technical book that could guide newcomers from entry to mastery, and from theory to practice. This would not only save the company the cost of training newcomers, but also leave space for newcomers to learn and grow on their own.
With this original intention in mind, I spent nearly a year in my spare time reviewing and summarizing the growth process and project experience of myself and my colleagues from Xiaobai to qualified algorithm engineers, and finally wrote this book by combining theory with practice. I hope my limited experience can really help readers who are interested in machine learning algorithms.
Features of this book
The biggest feature of this book is the combination of theory and practice. The first five chapters introduce the basic theoretical knowledge of machine learning algorithms. In addition to focusing on typical feature engineering methods and basic machine learning models, it also summarizes the construction of machine learning projects in the industry. The process often involves business disassembly methods, model evaluation and selection methods, and common model optimization methods. After readers have mastered a certain theoretical foundation of machine learning, they can then practice with the practical cases in Chapters 6 to 9. The four practical cases include common business scenarios in the industry, guiding readers step by step to gain an in-depth understanding of the business scenarios, and combine them with public data sets for data analysis, feature mining, model construction, etc. When readers truly understand the theoretical basis explained in this book from beginning to end and practice accordingly, they will be able to avoid many detours in learning machine learning algorithms. Whether it is the theoretical part or the practical part, I have given corresponding application codes. Readers can practice while reading the book to deepen their mastery of theoretical knowledge.
Advanced practice of machine learning: computational advertising, supply and demand forecasting, intelligent marketing, dynamic pricing overall structure of this book
The overall structure of this book is divided into two parts. The first part is basic theory, which focuses on the basic knowledge required for machine learning projects; the second part is practical cases, which explains in detail the practical process of basic theoretical knowledge through four practical cases of machine learning.
Target readers of this book
This book mainly targets the following three types of readers:
1) Fresh graduates in computer-related majors. This book introduces the basic theoretical knowledge and practical cases of machine learning algorithms, which can effectively help fresh graduates in computer-related majors quickly master relevant algorithm principles. At the same time, it combines practical cases to supplement the algorithmic practical abilities that fresh graduates lack.
2) Readers across majors who want to work on machine learning algorithms. This book tries its best to use simple and easy-to-understand language and a straightforward style to explain the complex principles of machine learning algorithms, helping readers quickly build a systematic understanding of machine learning algorithms from scratch. It also provides business cases to help cross-professional readers quickly understand common Internet problems. business scenario.
3) Algorithm engineer. For algorithm engineers with certain experience, this book is more like a handy tool book. It covers the basic knowledge of machine learning algorithms and model optimization iteration paths for common business scenarios as comprehensively as possible, and can help experienced algorithm engineers Review the past and learn the new.
Purchase link
Lottery method
- Like + favorite the article
- Leave a message in the comment area: "Life is short, refuse to be involved" or anything else (you can only enter the prize pool by leaving a message, and each person can leave a maximum of three messages)
- 5 people will be randomly drawn at 8pm on Friday night this week
comminicate
Friends who are interested in software exams can join the bloggers' communication group. There are currently four groups: software designers, senior experts, system architects, and system analysts.
- There are past papers, e-books and other materials in the group that you can pick up;
- No marketing, pure communication group;
- There will be book delivery activities twice a week, with three books at a time and free shipping to your home.