Course syllabus

TEK615 - SUPPLY CHAIN ANALYTICS

Course offered by the Department of Technology Management and Economics to the Bachelor Program

Industriell Ekonomi

7.5 Higher Education Credit Units

Spring term 2024

	Examiner	Ivan Sanchez-Diaz	ivan.sanchez@chalmers.se
	Instructors	Hendry Raharjo	hendry@chalmers.se
		Ivan Cardenas	ivandar@chalmers.se
		Mostafa Parsa	mostafap@chalmers.se
	TA	Juan Pablo Castrellon	juanpabl@chalmers.se
	Course assistants	Jonathan Axelsson	jonaaxe@student.chalmers.se
		Ludvig Nordberg	ludvigno@student.chalmers.se
		Marcus Wassenius	marcuswa@chalmers.se
		Noa Sjöstrand	noasj@student.chalmers.se
		William Bergquist	willbe@student.chalmers.se

Course description and aim

Supply chains create a vast amount of data every day. Every transaction, every operation, and every claim is often recorded and saved as data. Learning how to analyse these data and convert them into insight for decision-making can lead to higher revenues and better services for organisations.

Although supply chain data has been analysed for several years, new developments in technology (e.g., increased use of sensors, developments in intelligent systems, extended use of social networks) and the availability of tools for data analysis (e.g., data storage, visualisation, artificial intelligence) have increased the relevance of supply chain analytics in the recent years.

This course aims to provide an introduction to multiple methods and tools related to supply chain analytics that will allow the students to identify how supply chain analytics can benefit an organisation, identify what specific method should be applied to solve a specific problem, use existing software to analyse data and interpret the results.

Students are expected to understand the mathematics underlying the different methods and are expected to develop basic software programs. However, this course does not focus on mathematical derivations or developing complex codes. Python was selected as the main programming language for the course. Ready-to-use codes are given to the students, but it is the student’s responsibility to understand the input/outputs of the codes, and how these codes use the data.

Learning outcome

After completion of the course, the student should be able to:

• Use several common quantitative models to address problems and challenges within supply chains.
• Use popular analytics tools (e.g., Python) to analyse and visualise data.
• Develop and analyse the outcome of predictive models in supply chain management problems.
• Apply prescriptive models based on mathematical optimisation to solve supply chain management problems (inventory management, transport planning, among others).

• Understand the basics of machine learning and how this can be applied to supply chains.

Schedule

The course will take place during term 4 in the Spring of 2024. The course will follow a Block B schedule, with lectures on Tuesdays and Thursdays from 13:15-17:00, and Fridays from 13:15 to 15:00. Detailed schedule with information about the sessions is available here.

Content

The course will be structured in different modules in addition to some introductory topics and recap.

The first module (descriptive analytics) will focus on learning different tools to extract, describe and visualise data, including machine learning algorithms for clustering data. The second module (predictive analytics) will start by introducing the role of statistics in handling uncertainty in supply chain management and then will focus on estimating regression and time-series analyses to forecast outcomes in supply chain management problems. The third module (prescriptive analytics) will introduce optimisation and simulation models to improve decisions in transport and inventory management.

The course will include theory lectures, in-class workshops, business cases, and group presentations of in-class assignments. 

Lectures

Theory lectures will introduce the topics and tools to be used during in-class workshops and business cases. A topic may require more than one session based on the design content and schedule available here. Plan to attend lectures involving in-class workshops as they involve compulsory individual assignments, i.e., in-class submission. If you cannot attend you should ask the examiner for a compensatory assignment.

Supporting articles and relevant material will be distributed by instructors. Some of the course content will be based on:

Liu, Kurt. (2022). Supply Chain Analytics. Concepts, Techniques and Applications. Palgrave Macmillan. https://doi.org/10.1007/978-3-030-92224-5.

Warm-calls

During specific lectures, marked with (W) in the schedule, the teacher will ask questions to students using the warm-calls technique, i.e., every time, a different group of previously noticed students will be asked during the lecture. Participation in the warm calls is graded individually by pass/fail. Warm-call students' allocation is available here. 

In-class workshops

Nine (9) selected lectures will involve in-class workshops requiring mandatory submissions to train analytical and programming skills for the addressed topics. These submissions are expected to be completed individually during the workshop. Support from Python monitors and lecturers is provided during the session. Students should submit the Colab notebook and/or the link to a dashboard with the code and answers to the questions. Grading criteria for pass/fail will consider that each assignment was an individual/original work, it is complete, responses were justified, and the code runs. 

After the workshop, discussions about the assignment will be conducted, accompanied by presentations addressing the assignment solutions made by students in groups (see Group Presentations section). This mechanism serves to provide feedback on the submissions, with grading determined on a pass/fail basis.

The in-class assignments are one of the key activities in the course. If you are unable to attend a session where an in-class assignment is scheduled due to reasons communicated to the examiner, you have the option to complete the assignment independently and submit it via email to the examiner (Ivan Sanchez-Diaz) and the TA (Juan Pablo Castrellon) within one week following the missed session. You must check that you are not assigned to present an in-class assignment that you didn’t submit. You can check which day you have to present your in-class assignment on the assignments page on Canvas.

In-class communication: Support from course assistants regarding Python or Tableau will be available during the lectures and workshops. The course has created a Slack channel to ease live communication. See instructions on how to make the most of this communication platform here.

Business Case Studies

The course includes four sessions organised around business case studies, i.e., Freemark Abbey Winery, Wish Marketplace, Pligrim Bank and Race. In these student-centred sessions, students read a real-life business case in a handout that the teachers distribute in advance and prepare the questions proposed. Key learning points will be derived from students’ responses after cold calls. All the students must read the instructions and when indicated prepare the cases in advance. Instructions are available here.

Cold-calls

During business case studies the teacher will ask questions to students using the cold-call technique, i.e., students will be asked during the lecture to share their responses to the questions and to contribute to developing the lecture. It is important to be prepared for these sessions. If you feel uncomfortable being called reach out to the examiner via email.

Group Presentations 

Solutions to in-class assignments are presented to the entire class by groups of four (4) students during the week wrap-up sessions, typically scheduled on Fridays. Four (4) to five (5) groups per session will explain the solution to the assigned part of the submission following the lecturer's instructions. Groups for presentations have been randomly arranged. Students can find their groups and topics here. This activity is graded on a pass/fail basis.

Examination

To pass the course, students should get a passing grade in all nine (9) in-class assignments, the warm-call, and the group presentation. The grade will be determined by the score each student gets in the final written exam. Exam questions will span all the topics addressed in the course.