Analytics Project, Gasal 2024 - Part 2
Instructor: Mansur M. Arief, Ph.D.
This graduate course digs into the application of analytics to projects based on (semi)realistic datasets, guided by theories and algorithmic principles. In Part 2 of the course, students will focus on prescriptive analytics approaches (including linear and nonlinear programming one-shot decisions as well as sequential decisions), with a particular emphasis on optimization and decision-making algorithms. Building on the foundations laid in Part 1 (descriptive and predictive analytics), the course continues to prioritize hands-on group projects. This approach creates a sandbox learning environment where students can collaboratively apply their skills in ideation, modeling, and communication to solve complex, real-world challenges.
Course objectives
Upon the completion of the course, the students are able to
- identify real life problems that require analytics
- choose the appropriate methods or tools applicable to a certain problem
- apply tool and methods to address certain problem
- showcase the skills in presenting to results and explain the insights obtained from the projects
Lectures
- The lectures are on Fridays, 6:30-8:10pm WIB in Zoom (link posted in MyITS classroom).
- Attendance is required (by SIMT and ITS).
- Active participation is highly encouraged.
Office hours
Office hours (optional) are Saturday, 8am-9am WIB. During this time, feel free to use the “Office Hours” Zoom link to chat with me. If you want to meet with me outside of these hours, use this calendar.
Textbooks
NO required textbook for this course. I will provide reading materials in MyITS classrooms from chapters of the book we are currently preparing for this course. It is useful to consult materials from the following sources:
- Algorithms for Optimization (M. J. Kochenderfer and T. A. Wheeler) textbook (chapters available for free),
- Algorithms for Decision Making (Mykel J. Kochenderfer, Tim A. Wheeler, and Kyle H. Wray) available for free.
A great additional resource is the Engineering Design Optimization (Joaquim Martins and Andrew Ning) also available for free.
Other Resources
- Jupyter Notebook Examples
- Prescriptive Analytics Project (Book Draft)
- Project Webpage Template
- Project Gallery
Grading and assignments
Here is the grade breakdown for this course
| Assignment | Weight | Cumulative |
|---|---|---|
| Reflections (1 and 2) | 10% | 10% |
| Proposal presentation | 10% | 20% |
| Peer review | 10% | 30% |
| Midterm report | 15% | 45% |
| Final report | 25% | 70% |
| Final presentation | 30% | 100% |
| Project repo/website | 5% | (extra point) |
Please submit your assignments either by filling the form online or by uploading them in your MyITS. If it is a group assignment, only one submission is enough. The rubric for each assignment is linked in the table above and is also posted in MyITS classroom.
Schedule
| Week | Date | Session Details* | Assignment Due** | |
|---|---|---|---|---|
| 8 | Oct 18 | Overview, Prescriptive Analytics Projects (L) | - | |
| 10 | Nov 1 | Optimization Modeling (L) | Reflection 1 | |
| 11 | Nov 8 | Data Collection (L), Discussion (O) | - | |
| 12 | Nov 15 | Group 1 & 2 Proposal (P), Discussion (O) | Midterm report | |
| 13 | Nov 22 | Group 3 & 4 Proposal (P), Discussion (O) | Peer review | |
| 14 | Nov 29 | Group 5 Proposal, Data-driven Modeling (L) | Midterm feedback | |
| 15 | Dec 6 | Asynchronous Office Hours (O) | - | |
| 16 | Dec 13 | Final Presentation (P) and Remarks (L) | - | - |
| Dec 20 | Final presentation | |||
| Final report | ||||
| Reflection 2 |
AI usage policy
We are committed to fostering an environment where the responsible use of generative AI tools can enhance both learning and creativity. Here are the general guidelines to help you in integrating AI responsibly into the coursework:
- Freedom to Use AI: You are encouraged to use AI tools as you see fit. This trust is based on your demonstrated responsibility and initiative as learners adept at managing advanced technologies.
- Ethical and Responsible Use: It is essential to ensure that AI-generated content is accurate, unbiased, and respectful. You are expected to scrutinize the AI output for any issues such as plagiarism, bias, or inappropriate content and rectify these problems before submission.
- Transparency and Reflection in Usage: Every piece of work that includes AI assistance must have an accompanying AI Usage and Reflection Form.
- Seek Consent for Sensitive Data: Always secure consent before entering private, sensitive, or copyrighted information into any AI system, ensuring compliance with ethical standards and respect for privacy.
- Support and Resources: If you have any uncertainties about this policy or require assistance with AI tools, please do not hesitate to contact the teaching team. We are here to support your academic journey and ensure you can use AI effectively and ethically.
These guidelines are intended to enable you to contribute to a learning environment that values integrity, innovation, and critical examination. These practices not only enhance our academic endeavors but also prepare us for the ethical use of technology. I look forward to seeing how you creatively and responsibly integrate AI into your work, and I am always available to discuss any aspect of AI usage in your projects.
Late policy
Because of unexpected events, illnesses, work commitments, etc., there is a 0% penalty for 48 hours (no questions asked) after each assignment deadline (not presentations)— after which you receive 0 credit. Presentations do not have late days.
Disabilities
Students who may require academic accommodations due to a disability are encouraged to initiate their request with the SIMT course staff. The SIMT course staff will assess the request based on the provided documentation, recommend appropriate accommodations. It is advisable for students to contact the SIMT course staff as early as possible, as timely notification is essential to facilitate the coordination of accommodations.
Contact
I’m here to help you! If you have any questions or concerns:
- please email me at mansur (dot) maturidi (at) its (dot) ac (dot) id, or
- visit during office hours for a chat on Zoom.
I look forward to assisting you!
Acknowledgment
- This page is created using Jekyll.
- Some contents are edited from ChatGPT with the prompts “revise any grammatical errors and for better clarity” and Github Copilot auto complete.
- Most contents are adopted from the previous semester’s Analytics Project course webpage.
- The AI usage policy section is customized based on Stanford CTL workshop “AI in Education: Creating Your Course Policy” by Kenji Ikemoto.