Turn financial news, filings and transcripts into structured research signals using text processing, embeddings, transformer models and careful event-time alignment.
Duration7 weeks
LevelIntermediate
Modules7
Lessons28
This course teaches natural language processing techniques for financial text such as news articles, company filings and earnings call transcripts. You will move from classical text representations to transformer-based embeddings and classifiers, and learn how to align text events with market data without introducing lookahead. The course also covers entity linking, topic modeling and how to evaluate text-derived features in a research setting.
7 modules · 28 lessons · 7 weeks. Curriculum preview; the final syllabus may change before enrollment opens.
Build a sentiment classifier for financial headlines and compare it against a lexicon baseline
Create an entity-linked news dataset that maps articles to company identifiers with timestamps
Run an event study measuring market behavior around text-derived events and document its limitations
Quantzivo certificates are completion credentials issued by Quantzivo, not accredited qualifications. Courses teach technical and research skills; they do not promise investment returns or provide investment advice.
7 weeks7 modulesEngineer pipelines that collect, clean, deduplicate, tag and score financial news and text data, producing point-in-time sentiment datasets suitable for research.
10 weeks10 modulesEngineer LLM-based research agents that retrieve documents, call analytical tools and produce traceable financial research outputs with evaluation and guardrails built in.
7 weeks7 modulesApply supervised and unsupervised machine learning to financial datasets using feature engineering, purged cross-validation and disciplined, leakage-aware evaluation.
Reserve your place in a few steps, or ask us anything about the curriculum, schedule and format first.
