一、課程目標
1. 學習如何利用機器學習建立模型協助企業制定行銷決策。
2. 瞭解機器學習主要演算法的原理、使用目的與應用時機。
3. 針對行銷決策情境與內部數據資產，進行行銷大數據分析。
4. 解讀機器學習模型的有效性與產生行銷決策之洞察與意涵。
5. 學會操作SAS Viya進行機器學習之建模與分析結果解讀。
二、課程設計
本課程將學習如何運用自動化機器學習(Auto ML)之軟體建構機器學習模型以協助行銷決策。本課程將以教師課堂講授與示範方式，並由學生分組針對企業或市場上特定行銷議題進行資料蒐集或現有公開數據資料之擷取，利用SAS Viya進行建模分析，實際演練與應用本課程講授之分析方法。教學方法概述如下：
1. 教師課堂講授→由教師在課堂上針對大數據分析如何協助行銷決策、及機器學習（ML）主要演算法的基本概念、分析情境、及分析結果的解讀與應用，進行講授。
2. SAS Viya操作→由教師帶領學生在電腦上實際操作SAS Viya 中主要ML模型的建置與分析報表解讀。
3. 智慧行銷專題之實做→針對小組想探討的行銷問題，透過擷取市場數據資料庫或公開的數據資料進行建模與分析，產生關鍵資訊或情報，提出行銷決策之建議，並撰寫書面分析報告及進行口頭簡報。
1. Course objectives
1. Learn how to use machine learning to build models to help enterprises formulate marketing decisions.
2. Understand the principles, usage purpose and application time of machine learning.
3. Conduct large-scale marketing data analysis on marketing decision situations and internal data assets.
4. Explain the effectiveness of the reader machine learning model and the insight and implication of producing marketing decisions.
5. The learning will operate SAS Viya for modeling and analysis results of machine learning.
2. Course design
This course will learn how to use the software-constructing machine learning model of Automated Machine Learning (Auto ML) to assist in marketing decisions. This course will be taught and demonstrated by teachers, and students will collect data from specific marketing topics in the enterprise or market or extract existing public data. SAS Viya is used for modeling and analysis, and will practice and apply the analysis methods taught in this course. The teaching method is summarized as follows:
1. Teacher class lecture → The teacher will teach the classroom how to analyze how large data can assist in marketing decisions, as well as the basic concepts of the main algorithms of machine learning (ML), analysis situations, and the interpretation and application of analysis results.
2. SAS Viya operation → The teacher leads students to actually operate on the computer. The construction and analysis report of the main ML models in SAS Viya are explained.
3. Implementation of smart marketing topics → For marketing issues that the group wants to explore, model and analyze by obtaining market data databases or public data, generate key information or information, propose marketing decisions, and write a written analysis report and conduct oral briefing.
以自編教材為主
● 參考教材
1. SAS Institute (2023). Machine Learning Using SAS Viya Course Notes. North Carolina: SAS.
2.山口達輝、松田洋之 著，衛宮紘 譯（2020）。圖解AI：機器學習和深度學習的技術與原理。碁峰出版。
● SAS Viya操作影片
SAS官網部落格：Viya step by step操作教學。https://blogs.sas.com/content/sastaiwan/sas-viya/viya-線上影音教學/
● 其他參考資料
Kaggle數據建模和數據分析競賽平台：https://www.kaggle.com/
Mainly edited textbooks
● Reference textbooks
1. SAS Institute (2023). Machine Learning Using SAS Viya Course Notes. North Carolina: SAS.
2. Written by Yamaguchi Tatsuya and Matsuda Yoshi, Translation of the Palace of the Palace (2020). Illustration AI: The technology and principles of machine learning and in-depth learning. Published by Gifeng.
● SAS Viya operation video
SAS official blog: Viya step by step operation teaching. https://blogs.sas.com/content/sastaiwan/sas-viya/viya-online audio and video tutorial/
● Other reference materials
Kaggle data modeling and data analysis competition platform: https://www.kaggle.com/
| 評分項目 Grading Method | 配分比例 Grading percentage | 說明 Description |
|---|---|---|
| 平時作業平時作業 Normal operation |
20 | |
| 自主學習（第17及18周的學習表現）自主學習（第17及18周的學習表現） Independent learning (learning performance in weeks 17 and 18) |
20 | |
| 智慧行銷專題期末報告智慧行銷專題期末報告 Smart marketing topic final report |
40 | |
| 課堂參與（課堂出席率）課堂參與（課堂出席率） Class Participation (Course Attendance) |
20 |
