Numbering Code	U-ECON00 30030 SJ43 U-ECON00 40040 SJ43	Year/Term	2022 ・ First semester
Number of Credits	2	Course Type
Target Year		Target Student
Language	Japanese	Day/Period	Wed.5
Instructor name	AKITA YUYA (Graduate School of Economics Professor)
Outline and Purpose of the Course	With the development of information technology represented by the Internet, a large amount of data is generated for various phenomena, and utilization of such data is desired. This class will be held in a seminar format, and the students will learn various frameworks of information processing, i.e., pattern recognition, data mining, and machine learning. The students will also exercise a series of works, for example, defining the problems, selecting methods, and interpreting the results, using actual data.
Course Goals	The goal is to acquire basic knowledge in the field of data science, together with a set of skills that enables to set themes on their own and draw knowledge by information processing from the raw data in the real world.
Schedule and Contents	Practice a series of data processing where various methods of statistical analysis, pattern recognition, and machine learning are applied to actual data to obtain findings. Participants are divided into individuals or small groups of around two to four people, and each individual/group conducts exercises of analysis on their own themes of interest. The instructor advises on the details of the exercise, such as the subject, method and interpretation of the analysis. Basically, it is assumed that one theme will be tackled in each semester, depending on the difficulty of the theme participants chose. Seminars will generally be conducted according to the following schedule, both in the first and second semesters. However, the number of sessions will be changed as necessary. Note that pattern recognition and machine learning may not be familiar to many participants. For this reason, supplementary lectures may be offered according to participants' level of understanding. The total number of sessions, including a feedback session, is 15. Sessions 1-2: Group formation, deciding on themes Sessions 3-13: Report and review of Analysis (Every Time) Session 14: Final report (Presentation)
Evaluation Methods and Policy	Evaluation will be based on attendance at seminars (50 points) and presentation at the final report (50 points). Nonetheless, if the student is absent in one-third or more part of the seminar, no credits will be granted.
Course Requirements	It is desirable to have completed the course of Introduction to Information Processing, and have some degree of computer literacy, however, these are not mandatory conditions. It is recommended that the students have taken introductory courses of mathematics and statistics. The student must take this course throughout the school year, attending both the first and second semesters.
Study outside of Class (preparation and review)	Steady progress should be made in the tasks set in each session.
References, etc.	Introduce reference books suitable for the respective themes in the seminar, if necessary.