Search results

Find quantitative trading ideas and examine the research behind them

Model financial instruments with an inspectable quantitative library

Large Quantitative Models that use physics, chemistry, and scientific data to produce quantitative results.

Develop Python strategies with graphical backtesting and market gateways

Organize machine-learning experiments for quantitative investment research

Explore supplied datasets through classical and Bayesian statistical analyses in a graphical application.

Analyze text collections quantitatively

Examine stock-factor returns, predictive relationships and turnover

Build event-driven market simulations with a shared strategy engine

Search public trading disclosures and compare the dates behind them

Compare allocations using volatility, downside losses and drawdown risk

Turn financial text into structured events and sentiment data

Turn existing open-text feedback into a reviewed topic structure, segment comparisons and shared reports.

Code and compare qualitative material with quantitative descriptors in a shared research project.

Select market datasets by instrument, interval and observation type

Research and backtest quantitative strategies in notebooks and code

Inspect the product, model and market inputs behind a valuation

Maintain event-driven Python backtests with the Zipline research model

Host coded or visual strategies through shared broker connections

Run configurable pricing, risk and valuation-adjustment studies

Research trading decisions with reinforcement-learning experiments

Investigate product behavior and connect the findings with in-app engagement.

Prepare supplied business datasets, fit statistical models and regenerate tables or reports from analytical code.

Explore supplied business and process data through statistical procedures, interactive views and explanatory output.