Centrale Méditerranée
Sitraka FORLERCentrale Méditerranée · AMSE

Machine Learning, DDEFI track

Example

Predicting an asset price: time series, XGBoost and news sentiment

An end-to-end project example, to read before choosing a finance subject, reference deck
Centrale Méditerranée, Château-Gombert technology park, Marseille

to predictknown pastpricedayslog returnwalk-forward cutsimulated random walk, not a quote
Figure 1: a simulated price and its log returns: the price drifts, the returns oscillate around zero. Learn on the known past, predict the shaded zone, then move the cut forward.

Open the session

Each session has its own password, given in class. Capitals, spaces and hyphens do not matter. The slides are encrypted: nothing can be read without it.

In this session

  1. Framing: which decision, which horizon, which metric
  2. Time series: returns, stationarity, walk-forward validation
  3. XGBoost on lagged features
  4. Sentiment of financial and geopolitical news, and the combination
Introduction14 October 2026Tools14 October 2026Session 114 October 2026Session 214 October 2026Session 315 October 2026Session 415 October 2026Homework 1Milestone 1 (graded out of 5)Session 515 December 2026Session 616 December 2026Session 716 December 2026Homework 2Milestone 2 (25%)Session 812 February 2027Homework 3Final presentationSession 911 or 12 February 2027ThreadReferenceExampleReferenceThe codeReferenceProjectsReferenceHandbookReferenceInfraReferencePanoramaReferenceDeep learningReference
Figure 2: the thread of the course; this session is highlighted.
SessionTitleDate
IntroductionAI at a crossroads: history, troughs, jobs, and you14 October 2026Open
ToolsKaggle, GitHub, Python: your tools, your accounts, your repository14 October 2026Open
Session 1Frame before you model, then least squares14 October 2026Open
Session 2Likelihood, generalisation, project kick-off14 October 2026Open
Session 3Convex optimisation and regularisation15 October 2026Open
Session 4Decide under cost, ship a reproducible repository15 October 2026Open
Homework 1Milestone 1: your project and its problem statement (graded out of 5)Milestone 1 (graded out of 5)Open
Session 5Finishing Titanic together, kernels, SVM and decision trees15 December 2026Open
Session 6Forests, boosting and the honest comparison16 December 2026Open
Session 7Explain, audit fairness, discover without labels16 December 2026Open
Homework 2Milestone 2 (25%): an OLS or a simple classification on your projectMilestone 2 (25%)Open
Session 8Neural networks, drift, conformal prediction, going live12 February 2027Open
Homework 3Final presentation with the code (50%): the delivered projectFinal presentationOpen
Session 9Final presentation day: the defences11 or 12 February 2027Open
ThreadThe running thread, step by step: the default-score repository, in screenshotsReferenceOpen
ExamplePredicting an asset price: time series, XGBoost and news sentimentReference
The codeThe code of every model: import, download by API, fit, predictReferenceOpen
ProjectsOpen data and machine learning projects by sector: finance, insurance, logistics, tech, sportReferenceOpen
HandbookThe data and AI expert handbook: scope, tool up, model, deploy, observeReferenceOpen
InfraData engineering, SRE and cloud: the commands, the principles, the jobs, from junior to expertReferenceOpen
PanoramaA panorama of models: which ones, what for, in which sectorsReferenceOpen
Deep learningDeep learning, the essentials: key concepts, why they matter, the maths on the board, and a mini tutorialReferenceOpen

Table 1: the sessions of the course, in order; each one opens with its own password.