Spotcap BAI is an off-the-shelf web service application that provides real-time in-depth bank account analytics on SMEs including a determination of an eligible credit limit, probability of default, profiling, adverse transaction categorisations, segmentation analysis and other factors.
Spotcap BAI is an off-the.shelf web service application that provides real-time in-depth bank account analytics on SMEs including a determination of an eligible credit limit, probability of default, profiling, adverse transaction categorisations, segmentation analysis. and other factors.
Based on the customer‘s available capital and average liquidity buffer. A range is provided to account for different product terms.
Derived applying machine learning techniques using the customer‘s cash profile, based on several years of SME loan performance across countries and 200+ unique attributes tied into a strong performing risk model.
Including transactions characteristics, balance volatility, outflow deviation and balance drops.
Assessment of transaction semantics and model customisation possible for premium version.
All inflows and outflows for the period of consideration including main semantics labels to detect adverse borrower information (e.g. new lending obligations, dishonoured payments, etc.,) which impact the likelihood of default.
Bank Risk Analytics Model incorporates various insights provided from peer comparisons, highlighting balance volatility and sudden drops, as well as inflow and outflow deviations.
Based on clustering approaches, all main inflows and outflows are grouped to detect concentration risks and trends related to both customers and suppliers.
Additional statistics are applied to measure the stability of various key bank account aspects. Leverage of population stability index (PSI) as a metric to measure shifts in the bank account profile over time comparing the period pre-COVID-19, lockdowns and the current situation.
Based on the customer‘s available capital and average liquidity buffer. A range is provided to account for different product terms.
Derived applying machine learning techniques using the customer‘s cash profile, based on several years of SME loan performance across countries and 200+ unique attributes tied into a strong performing risk model.
Including transactions characteristics, balance volatility, outflow deviation and balance drops.
Assessment of transaction semantics and model customisation possible for premium version.
All inflows and outflows for the period of consideration including main semantics labels to detect adverse borrower information (e.g. new lending obligations, dishonoured payments, etc.,) which impact the likelihood of default.
Bank Risk Analytics Model incorporates various insights provided from peer comparisons, highlighting balance volatility and sudden drops, as well as inflow and outflow deviations.
Based on clustering approaches, all main inflows and outflows are grouped to detect concentration risks and trends related to both customers and suppliers.
Additional statistics are applied to measure the stability of various key bank account aspects. Leverage of population stability index (PSI) as a metric to measure shifts in the bank account profile over time comparing the period pre-COVID-19, lockdowns and the current situation.
