Situation
Free per-stock Casablanca Stock Exchange history is fragmented, and existing sources rarely connect price data to risk context or explain uncertainty rather than predicting price.
Financial Analytics
Casablanca Risk
A Casablanca Stock Exchange risk-intelligence platform combining a 124,562-row historical panel, stock and portfolio risk analysis, volatility and regime models, simulation, and structured news context.
View source repository↗
Why it matters
Makes local market exposure and uncertainty understandable without presenting risk analytics as price prediction or investment advice.
My role
Financial data analyst and solution developer
- 01Engineered quote and financial-news collectors with Requests, Beautiful Soup, Pandas, source adapters, robots.txt checks, caching, scheduling, validation, deduplication, and failure-safe atomic writes.
- 02Assembled and validated 124,562 daily observations across 78 symbols, delayed quotes, issuer references, portfolio records, and multilingual financial news.
- 03Implemented stock, market, tail, liquidity, regime, portfolio, simulation, and event-level risk analysis with explicit validation and investability gates.
- 04Translated risk evidence into rankings, profiles, portfolio scorecards, news context, and virtual trading without presenting analytics as price prediction.
Task
Build a risk-intelligence platform that assembles a reliable local-market panel, quantifies stock and portfolio risk, and translates it into decision support, without presenting analytics as price prediction or investment advice.
Action
- Python collectors built with Requests, Beautiful Soup, and Pandas retrieve delayed quotes and French/Arabic financial news from Casablanca Bourse, AMMC, Medias24, L'Economiste, Boursenews, Finances News Hebdo, and La Vie Eco, respecting robots.txt, caching raw HTML, and writing atomically so a failed refresh never corrupts the last valid snapshot. The resulting panel holds 124,562 daily observations across 78 symbols from January 2015 to June 2026.
- Stock and market risk are measured with annualised volatility, Sharpe ratio, maximum drawdown, beta to MASI, historical VaR, and Expected Shortfall, while Amihud illiquidity and coverage checks gate stale or hard-to-trade names out of portfolio conclusions. GARCH forecasts volatility and HMM identifies market regimes, with Kupiec backtesting checking VaR exceedances.
- Equal weight, minimum variance, Hierarchical Risk Parity, and MASI buy-and-hold portfolios are compared with Ledoit-Wolf covariance shrinkage and out-of-sample walk-forward testing. The latest run shows minimum variance at roughly 11.0% annualised return, 11.5% volatility, and a 0.75 Sharpe ratio, versus about 5.4%, 13.3%, and 0.28 for MASI buy-and-hold. A 10,000-path Monte Carlo simulation reports a full outcome distribution: about 35.7% probability of loss, 6.5% median return, and a negative 14.9% median maximum drawdown.
- Market-model event studies calculate abnormal returns and CAR windows around news, while deterministic company, sector, and theme mappings attach auditable risk or opportunity tags to French and Arabic financial news, without issuing buy or sell signals.
Result
The platform surfaces that domestic diversification can be limited by bank and telecom concentration, while the MASI's lower correlation with global indices may make Moroccan equities more relevant for international diversification. It is delivered through searchable snapshots, risk profiles, rankings, and a virtual trading simulator that keep uncertainty and data limitations visible rather than hidden.
Technical implementation
How the solution was built.
Each layer connects an implementation choice to the decision or workflow it supports.
07 layers| Layer | Implementation | Operational purpose |
|---|---|---|
| Market collection | Requests, Beautiful Soup and source-specific adapters for delayed quotes and issuer data | Build a consistent local-market panel from fragmented public sources |
| News collection | French and Arabic financial-news scraping with normalized headlines, provenance and cross-source deduplication | Connect market analysis to traceable company, sector and macro context |
| Data reliability | robots.txt checks, raw-response caching, schema validation, lock files, scheduling and atomic writes | Preserve the last valid dataset and expose stale or failed refreshes honestly |
| Risk measurement | Volatility, beta, drawdown, historical VaR, Expected Shortfall, correlation and liquidity indicators | Compare stock and portfolio exposure with interpretable downside measures |
| Risk modelling | GARCH volatility forecasts, HMM regimes and Kupiec VaR backtesting | Estimate changing risk conditions and verify whether loss thresholds remain credible |
| Portfolio analysis | Minimum variance, Hierarchical Risk Parity, Ledoit-Wolf covariance and walk-forward testing | Compare allocations using out-of-sample evidence, costs and investability gates |
| Simulation and events | 10,000-path Monte Carlo distributions and market-model event studies | Quantify ranges of outcomes and examine abnormal behaviour around news events |
Product walkthrough
Screens connected to decisions.
concept art
Sets the visual direction for the platform before the functional screens that follow.
market snapshot
Makes the listed market searchable and comparable through price, volume, capitalization, and recent movement.
stock detail
Combines historical price context with market value, traded value, and relative-risk indicators.
stock risk profile
Translates volatility, VaR, expected shortfall, and drawdown into a readable risk profile.
stock news disclosures
Connects company-level disclosures and sentiment context to the security being examined.
news risk context
Maps news to stocks, sectors, and macro themes to distinguish risk signals from opportunity context.
practice account summary
Keeps virtual cash, invested capital, positions, and return visible before entering the simulator.
tracked risk ranking
Ranks tracked securities by comparable risk measures instead of implying price direction.
paper trading simulator
Lets users test their own analysis with virtual money, delayed prices, and explicit transaction costs.
holdings risk scorecard
Connects position-level P&L with portfolio concentration, weighted volatility, and beta.
news signal details
Expands each article into traceable risk and opportunity tags with source and confidence context.