Syllabus — Finance Project — Asset Management
Summer 2026
Course information
| Title | Finance Project — Asset Management |
| Term | Summer 2026 |
| Level | Master |
| ECTS | 6 |
| Instructors | Prof. Dr. Andre Guettler, Oliver Padmaperuma |
| Contact | oliver.padmaperuma@uni-ulm.de, CC andre.guettler@uni-ulm.de |
| Location | Helmholtzstraße 18, room E60, Ulm |
| Time | Wednesdays 12:15–13:45 |
| Language | English |
Course objectives
This course teaches students to build an end-to-end empirical asset-management research pipeline in R and to apply it to a non-traditional asset class: prediction markets. Students master the core ML toolbox — linear regression, Ridge, Lasso, Elastic Net, and resampling-based model assessment — then design their own indicator library on the Polymarket Quant Bench (curated OHLCV bars built on Jon Becker’s polymarket-data dump), derive trade signals, back-test, and critically reflect on what works.
Learning outcomes
By the end of this course, students will be able to:
- Design and execute a full empirical workflow in R: load, clean, model, back-test, report.
- Apply Ridge, Lasso, and Elastic Net regularisation, and pick hyper-parameters via cross-validation.
- Engineer technical / statistical / external-data indicators for time-series of prediction-market prices.
- Implement a simple back-test honestly (including transaction-cost framing) and interpret performance metrics.
- Communicate empirical findings in writing (R Markdown → PDF) and orally (20-minute presentation).
Prerequisites
- Comfort with basic statistics and linear regression
- Some prior coding experience (any language) — we ramp up R from scratch in Lecture 2
- A laptop with R, RStudio, and the recommended packages installed before Lecture 2
Required materials
- R + RStudio (free, see https://posit.co/download/rstudio-desktop)
- Reference text: James, Witten, Hastie, Tibshirani — An Introduction to Statistical Learning with Applications in R (free PDF at https://www.statlearning.com)
- Dataset: Polymarket Quant Bench on HuggingFace (CC-BY-4.0; built on Jon Becker’s polymarket-data). Public access — pull with
hf downloadahead of Lecture 5
Timetable
| Week | Date | Lecture | Topics |
|---|---|---|---|
| 1 | Apr 15, 2026 | Lecture 1: Foundations | Course aim & organisation, Backtesting overview & case study, In-sample tests (Welch & Goyal 2008), Out-of-sample (walk-forward, R²_OS), Useful predictors & p-hacking |
| 2 | Apr 22, 2026 | Lecture 2: Introduction to R | Why R for empirical asset-management research, RStudio and the script editor, Variables, vectors, matrices, data frames, lists, Functions and loops, Data import and export |
| 3 | Apr 29, 2026 | Lecture 3: Assessing model accuracy & Ridge regression | Statistical learning: Y = f(X) + ε, Quality of fit and the train/test MSE distinction, Bias-variance trade-off and overfitting, OLS limits: prediction accuracy & interpretability, Ridge regression and the L2 penalty |
| 4 | May 6, 2026 | Lecture 4: Lasso, cross-validation & Elastic Net | Lasso: L1 penalty and exact-zero coefficients, Cross-validation: validation set, LOOCV, K-fold, Choosing the optimal λ for Lasso, OLS post-Lasso for cleaner coefficient inference, Elastic Net — combining Ridge and Lasso |
| 5 | May 13, 2026 | Lecture 5: Prediction markets, the Polymarket Quant Bench & your project | Prediction markets — definition and Polymarket as the canonical venue, How prices form: liquidity, resolution, mechanics, The Polymarket Quant Bench dataset (HuggingFace): access and schema, First look at the data in R, Your project: indicator design, back-test, deliverables, R toolbox |
| 13 | Jul 1, 2026 | Lecture 6: Final presentations | Presentation order and time budget, Q&A rules, Closing thoughts and feedback |
Adding a new lecture folder under
lectures/automatically updates this table — no manual edits needed.
Assessment & grading
| Component | Weight |
|---|---|
| Project (Rmd code + knitr-rendered PDF report) | 50% |
| Final presentation (20-minute group, PDF slides) | 50% |
| Total | 100% |
Grading scale: German scale 1.0 (excellent) – 5.0 (fail). 4.0 is passing.
Group size: 3 students. If you don’t have a preference, we will allocate you.
Policies
Attendance
Attendance at all five teaching sessions is strongly recommended. Attendance at the final presentations session (1 July 2026) is mandatory for all groups.
Late submissions
The submission deadline (30 June 2026, 18:00) is firm. Late submissions are graded down by one full grade (1.0) per started 24-hour period.
Academic integrity
All work must be the declared group’s own. Plagiarism and unauthorised AI use will be referred to the examination office. Citing AI-assisted work where permitted is required. Code submitted with a project must run as-is on the data we provide; we may spot-check by re-running the Rmd.
Coding style
We expect well-commented, self-explanatory, efficient R code: meaningful variable names, no for-loops where vectorised alternatives exist, helper functions for repetitive tasks (each annotated with a one-line comment stating what the function does and returns). The demo code we ship is intentionally basic; copying it without elaboration is not enough.
Accommodations
Students requiring accommodations should contact the instructor in the first week of term.
Contact
- Course-content questions: ask in class (preferred) or email oliver.padmaperuma@uni-ulm.de, CC andre.guettler@uni-ulm.de.
- Submissions: zip-folder named
Asset2026_surname1_surname2_surname3containing your Rmd, the PDF report, and the PDF slides. Email the same address pattern with the same subject line. - Admin / exam-eligibility questions: studiensekretariat@uni-ulm.de.
- Technical (Moodle / IT) questions: helpdesk@uni-ulm.de.
- Moodle: all announcements and the dataset link are posted on the course Moodle page.