(in Polish) Analizy i decyzje finansowe z wykorzystaniem narzędzi sztucznej inteligencji 2400-ZEWW979
-Key differences between major LLMs, trade-offs between cost, performance, and capabilities.
-LLM specifications and suitability in specific use cases.
-Structure of effective financial prompts, advanced prompting techniques for complex financial analysis.
-Prompt engineering for financial queries, data integration in financial prompts.
-Python packages for financial applications; connecting to financial APIs, using AI to generate market data summaries.
-AI-powered financial statement analysis; income statement, balance sheet, and cash flow analysis.
-Automated ratio calculations, trend and industry analysis, EDGAR database integration, cross-company analyses.
-AI driven data visualization techniques in financial analysis.
-Comprehensive AI workflows for investment research.
-Explore and visualize investment strategies performance and risk using AI techniques.
-Time series preprocessing, normalization, handling missing data in financial datasets.
-Transformer and foundation models for financial time series, implementing transformer architectures for multi-horizon return forecasting.
-Portfolio optimization using AI enhancements for Markowitz optimization and Black-Litterman implementation.
-Practical considerations in designing quantitative investment strategies.
-Designing, implementing and backtesting technical trading strategies with AI, financial metrics for strategy assessment.
-Designing and analyzing investment strategies through specialized prompting.
Type of course
Course coordinators
Learning outcomes
On course completion the student knows how to:
-Compare major LLMs for financial applications and evaluate cost-performance trade-offs for specific use cases
-Design and optimize sophisticated prompts for financial analysis using advanced techniques
-Build AI workflows for comprehensive financial statement analysis, ratio calculations, and multi-company comparisons
-Create dynamic, interactive visualizations and automated financial reports with AI-generated narrative insights
-Apply transformer architectures and foundation models to financial forecasting with proper preprocessing and evaluation techniques
-Implement AI-enhanced portfolio optimization techniques including Markowitz and Black-Litterman models
-Design, implement, and backtest trading strategies with proper risk management and performance evaluation frameworks
Assessment criteria
Written assignments during the course
Bibliography
Author’s materials, Python packages documentation
Additional information
Additional information (registration calendar, class conductors, localization and schedules of classes), might be available in the USOSweb system: