Quantitative Researcher | Risk Magazine Quant of the Year 2024
Quantitative researcher focused on systematic strategies, portfolio optimization, and stochastic volatility modeling. Currently Global Head of Quantitative Analytics at LGT Private Banking. Co-originator of the Robust Optimisation of Strategic and Active Asset Allocation (ROSAA) framework and the log-normal beta stochastic volatility model.
For publications, speaking, and full background → artursepp.com
QuantInvestStrats (qis)
Quantitative Investment Strategies (QIS) package implements Python analytics for visualisation of financial data, performance reporting, analysis of quantitative strategies.
Features:
- Financial data visualization
- Performance reporting and analytics
- Quantitative strategy analysis
- Portfolio construction tools
OptimalPortfolios (optimalportfolios)
Implementation of optimization analytics for constructing and backtesting optimal portfolios in Python. Companion code to Sepp (2023) and Sepp, Ossa & Kastenholz (2026)
Features:
- Portfolio optimization algorithms
- Risk budgeting implementation
- Backtesting frameworks
- Performance attribution
StochVolModels (stochvolmodels)
Python implementation of pricing analytics and Monte Carlo simulations for stochastic volatility models including Karasinski-Sepp log-normal stochastic volatility model and Heston volatility model. Companion code to Sepp & Rakhmonov (2023).
Features:
- Karasinski-Sepp log-normal stochastic volatility model
- Heston model
- Monte Carlo simulations
- Analytical valuation of European call and put options
factorlasso (factorlasso)
Sparse factor model estimation with sign-constrained LASSO, prior-centered regularisation, and hierarchical group LASSO (HCGL) with integrated factor covariance assembly. Companion code to Sepp, Ossa & Kastenholz (2026) and [Sepp, Hansen & Kastenholz (2026)].
Features:
- Sign-constrained LASSO and Group LASSO via CVXPY
- Prior-centered regularisation (shrink toward β₀, not zero)
- Hierarchical Clustering Group LASSO (HCGL) with auto-discovered groups
- NaN-aware estimation for variables with different history lengths
- Consistent factor covariance assembly (Σ_y = β Σ_x β' + D)
- scikit-learn compatible API (fit / predict / score)
Features:
- Sign-constrained LASSO and Group LASSO via CVXPY
- Prior-centered regularisation (shrink toward β₀, not zero)
- Hierarchical Clustering Group LASSO (HCGL) with auto-discovered groups
- NaN-aware estimation for variables with different history lengths
- Consistent factor covariance assembly (Σ_y = β Σ_x β' + D)
- scikit-learn compatible API (fit / predict / score)
BloombergFetch (bbg-fetch)
Python functionality for getting different data from Bloomberg: prices, implied vols, fundamentals.
Features:
- Bloomberg data fetching wrapper
- Price data retrieval
- Implied volatility data
- Fundamental data access
- Built on xbbg package integration
VanillaOptionPricers (vanilla-option-pricers)
Python implementation of vectorised pricers for vanilla options
Features:
- Black-Scholes log-normal option pricing
- Bachelier normal option pricing
GoalBasedAllocation (goal-based-allocation)
Analytical Laplace-transform framework for dynamic mean-variance portfolio allocation under regime-switching jump-diffusions with absorbing wealth floors. Companion code to Sepp (2026).
Features:
- Riccati ODE system for MV-optimal policy with regime-dependent coefficients
- Terminal wealth density decomposition (survived + floor atom + overshoot)
- Exact buy-and-hold moments via matrix exponential
- Investment opportunity set construction with endogenous de-risking glide paths
- Monte Carlo simulator for validation
| Package | Stars | Forks | Total Downloads | Monthly |
|---|---|---|---|---|
| QuantInvestStrats |  |
 |
 |
 |
| OptimalPortfolios |  |
 |
 |
 |
| StochVolModels |  |
 |
 |
 |
| factorlasso |  |
 |
 |
 |
| BloombergFetch |  |
 |
 |
 |
| VanillaOptionPricers |  |
 |
 |
 |
| GoalBasedAllocation |  |
 |
 |
 |