Skip to main content
RS

Risknowledge SA

Risknowledge offers advanced risk model validation tools that quantify the discrepancy between predicted and realized portfolio risk. Their platform helps financial institutions estimate and manage true risk by determining the significance of model performance. This allows for more accurate risk assessment and improved portfolio management.

Founded 2024250+ followers
Updated 3 months ago

Funding

Funding not disclosed

Funding rounds are not available yet.

Founders

Founder details are not available yet.

Product

Problem

Financial institutions rely on risk models to predict portfolio risk, but these models often produce idealized predictions that deviate from realized risk, leading to inaccurate risk assessments. Traditional model validation techniques may fail to quantify the discrepancy between predicted and actual risk, hindering effective risk management and potentially leading to inadequate capital allocation.

Solution

Risknowledge offers Overarch, a SaaS-based platform that provides advanced risk analytics for model validation, rectification, and selection, enabling financial institutions to estimate and manage true risk. Overarch employs ES Ridge Backtest methodologies to backtest Expected Shortfall, Value at Risk, and other risk measures, while also quantifying prediction discrepancies to estimate true risk. The platform is compatible with any distributional assumption of a client's risk model and is model-independent, representing an advanced model validation framework for distribution-based risk models. Model performance scorings, based on joint elicitability of VaR and ES, facilitate model selection among multiple challenger models.

Target Audience

The primary target audience includes financial institutions, risk managers, and quantitative analysts who need to validate risk models, estimate true risk, and improve portfolio management.

Features

  • SaaS-based platform for risk model validation, rectification, and selection
  • ES Ridge Backtest methodologies for backtesting Expected Shortfall and Value at Risk
  • Quantification of prediction discrepancies for estimation of true risk
  • Compatibility with any distributional assumption of client risk models (parametric, historical simulation, MonteCarlo, etc.)
  • Model-independent technology, agnostic to the real-world distribution of events
  • Model performance scorings based on joint elicitability of VaR and ES for model selection
  • Proprietary algorithms based on closed-form solutions for computational speed and scalability
  • Secure cloud infrastructure
This profile is AI-generated and may contain inaccuracies.