学部後期課程
HOME 学部後期課程 Data Science for Practical Economic Research
過去(2022年度)の授業の情報です
学内のオンライン授業の情報漏洩防止のため,URLやアカウント、教室の記載は削除しております。
最終更新日:2024年3月15日

授業計画や教室は変更となる可能性があるため、必ずUTASで最新の情報を確認して下さい。
UTASにアクセスできない方は、担当教員または部局教務へお問い合わせ下さい。

Data Science for Practical Economic Research

Data Science for Practical Economic Research
Despite its name, this class is on forecasting methods in economics and applications of machine learning methods to forecasting. A typical class on machine learning focuses on cross-sectional data, leaving almost no space for a discussion of how to work with time series data and how to make forecasts with such data. The purpose of this class is to cover this gap. This class might be useful for students who plan to work at financial companies and government entities tasked with making forecasts. We will closely follow the textbook by G. Elliott and A. Timmermann "Economic Forecasting". The book is quite advanced and requires good understanding of probability and statistics. During the lectures, we will cover chapters from this textbook and perform hands-on sessions. All homework assignments for this class will be practical: students will be asked to apply methods covered in the class to real datasets. The required programming language is Python.

Students taking this class will be assumed to be familiar with basics of Machine Learning, probability and statistics, as well as programming in Python.
MIMA Search
時間割/共通科目コード
コース名
教員
学期
時限
0704254
FEC-EC5801L3
Data Science for Practical Economic Research
Kucheryavyy Konstantin
S1 S2
月曜4限
マイリストに追加
マイリストから削除
講義使用言語
英語
単位
2
実務経験のある教員による授業科目
NO
他学部履修
開講所属
経済学部
授業計画
Preliminary plan of lectures (subject to change): Lecture 1: Loss Functions. Lecture 2: The Parametric Forecasting Problem. Lecture 3: Classical Estimation of Forecasting Models; Bayesian Forecasting Methods. Lecture 4: Model Selection. Lecture 5: Univariate Linear Prediction Model. Lecture 6: Vector Autoregressions. Lecture 7: Forecasting in a Data-Rich Environment. Lecture 8: Nonparameteric Forecasting Methods. Lecture 9: Binary Forecasts. Lecture 10: Forecast Combinations. Lecture 11: Desirable Properties of Forecasts.
授業の方法
Lectures. Demo programs.
成績評価方法
Grade will be based on homeworks.
教科書
– G. Elliott and A. Timmermann "Economic Forecasting" (Princeton University Press, 2006) - F.X. Diebold "Forecasting in Economics, Business, Finance and Beyond" (University of Pennsylvania, 2017) - Peter Fuleky (editor) "Macroeconomic Forecasting in the Era of Big Data: Theory and Practice" (Springer, 2020)
参考書
NA
履修上の注意
- Good command of Python is assumed. - Students are assumed to be familiar with basics of Machine Learning. - Students are assumed to have taken basic probability and statistics classes.