Currently, most expense reporting systems rely on catching undesirable expenses through a defined policy. Simple In/Out of Policy definitions of undesirable spend, however, are difficult to reliably use as definitions change over time and often according to each claim’s unique position and needs. This makes it challenging to manually flag anomalies.
Knowing the promise technology like AI holds, PredictX used machine learning models to enhance fraud detection in expense reporting for users of expense management and accounts payable automation provider, Emburse’s solutions.
Emburse brings together some of the world’s most powerful and trusted expense and AP automation brands, including Abacus, Captio, Certify, Chrome River, Nexonia and Tallie.
where a predictive model learns the characteristics of previously flagged transactions to predict future anomalous transactions that are not yet manually assessed.
where a holistic and open-ended analysis of all expense feed data points identifies suspicious transactions, even if they have not been detected in the past.
The cookie settings on this website are set to "allow cookies" to give you the best browsing experience possible. If you continue to use this website without changing your cookie settings or you click "Accept" below then you are consenting to this.