ScalAttrib™: ESG and macroeconomic financial models
Client situation
A Tier 1 leading AM in ESG and green investment would like to develop a clear AI-based methodology & tools in order to integrate ESG factors as a structuring element to anticipate profitability and manage medium and long-term risks.
They realize that they are dealing with ESG as an exogenous factor. They would like to understand the relationship between ESG factors and other quantitative driving factors (macroeconomic, microeconomic, etc.), and integrate their own qualitative knowledge in the model, in order to generate alpha.
Scalnyx solution
We customized our Projector™ platform based on their AM team experts needs to match their database and also their portfolio and risk analysis frameworks.They used the platform to build Causal AI models from non-linear factors such as ESG, micro/macro-economic, and in-house portfolio data. They tested the complex combination of factors and also elaborate on the complex mixture of environmental and economic factors. They assess the accuracy of each model with a back-testing framework.
The generated Causal AI model inferences are fully explainable and interpretable.
Client gain
The resulting Causal AI models improved by the domain experts knowledge (asset manager), outperformed the performance of classical linear models and other AI/ML techniques, proving the interest of quantamental investing if the asset manager disposes of the right tools.
The company appropriates the construction of their own tools and methodologies that match the company’s culture, governance, and team organization, and also their data providers and sources.
ScalFraud™: Causal Fraud Detection
Client situation
A leading financial institution was facing increasing pressure to improve the detection of terrorism financing activities. Traditional rule-based systems and black-box machine learning models struggled to adapt to evolving fraud patterns, lacked generalization to unseen cases, and offered limited explainability. With a small number of labeled fraud profiles and high-dimensional data, current tools showed performance bottlenecks and created operational risks due to opaque decision-making processes.
Scalnyx solution
Scalnyx introduced ScalFraud, a Causal AI agent specialized in fraud detection. Unlike conventional models, ScalFraud reveals the underlying causes of fraudulent behavior rather than just correlations. It combines expert knowledge with observed data to build a transparent, explainable model that identifies key causal drivers and simulates the impact of different variables. Using our proprietary platform, PROJECTOR™, we generated synthetic fraud profiles, selected the most influential variables, and created an interpretable model capable of detecting both known and emerging fraud patterns.
Client gain
With ScalFraud, the client significantly improved fraud detection performance while reducing false positives. The inclusion of synthetic yet realistic profiles helped the model generalize to novel threats. The use of causal reasoning allowed analysts and compliance officers to understand why a case was flagged, improving trust, regulatory alignment, and operational efficiency. This approach empowered the institution to make faster, more confident decisions in the fight against financial crime.
ScalScore™: Causal Credit Scoring and Risk
Client situation
Credit risk teams often face a tough trade-off: use complex machine learning models that offer high predictive power but lack interpretability—or rely on simpler models that are easier to explain but far less accurate. In both cases, the models indicate who is likely to default, but not why. These models also assume independent risk factors, leading to biased predictions, especially in cases where factors like industry sector play a hidden role. Missing data and unobserved variables further limit the effectiveness and fairness of current scoring systems.
Scalnyx solution
Scalnyx developed ScalScore, a Causal AI agent designed to revolutionize credit scoring. ScalScore delivers the accuracy of complex models with the transparency of simple ones—by modeling the true cause-effect relationships behind credit default. It identifies key causal drivers of risk, detects hidden biases, and explains predictions in a clear, auditable way. Even in the presence of missing data or unmeasured factors, ScalScore can simulate outcomes, perform stress testing, and ensure robust, regulator-ready decisions.
Client gain
With ScalScore, financial institutions gain a powerful edge: predictive performance on par with black-box models, combined with full interpretability for analysts and regulators. The model reveals not only individual risk levels but also systemic patterns—like clusters of borrowers exposed to the same underlying risks. As a result, clients improve credit risk assessment, reduce unjustified rejections, and deploy early warning systems for portfolio-level risk—all while meeting the highest standards of regulatory transparency.
Are you interested in one of our Business Agents, or you want to build your own Business Agent ?