Abstract: Various embodiments herein each include at least one of systems, methods, and software for in situ and network-based transaction classification. Such embodiments use advanced data analytics and machine learning techniques of consumer's transaction attributes to reduce shrink at checkout. One embodiment, in the form of a method, includes processing a dataset of transactions to identify normal transaction patterns and processing a dataset of transactions that included known fraud to identify variation patterns between the identified normal transaction patterns and the data of each transaction. The method further includes generating at least one pattern model based on the identified normal transaction patterns and the identified variation patterns. In such embodiments, each pattern model typically includes classification values for determining a likelihood of fraud in transactions.

Abstract: Various embodiments herein each include at least one of systems, methods, and software for in situ and network-based transaction classification. Such embodiments use advanced data analytics and machine learning techniques of consumer's transaction attributes to reduce shrink at checkout. One embodiment, in the form of a method, includes processing a dataset of transactions to identify normal transaction patterns and processing a dataset of transactions that included known fraud to identify variation patterns between the identified normal transaction patterns and the data of each transaction. The method further includes generating at least one pattern model based on the identified normal transaction patterns and the identified variation patterns. In such embodiments, each pattern model typically includes classification values for determining a likelihood of fraud in transactions.

Abstract: Various embodiments herein each include at least one of systems, methods, and software for in situ and network-based transaction classification. Such embodiments use advanced data analytics and machine learning techniques of consumer's transaction attributes to reduce shrink at checkout. One embodiment, in the form of a method, includes processing a dataset of transactions to identify normal transaction patterns and processing a dataset of transactions that included known fraud to identify variation patterns between the identified normal transaction patterns and the data of each transaction. The method further includes generating at least one pattern model based on the identified normal transaction patterns and the identified variation patterns. In such embodiments, each pattern model typically includes classification values for determining a likelihood of fraud in transactions.

Abstract: The various embodiments herein each include at least one of systems, methods, and software for discrete-event simulation for transaction service point device cash servicing, such as SSTDs. Such embodiments provide a unique, completely different analytic approach, and predicts a more detailed set of intractable insights for efficient servicing cash needs of SSTDs. One example embodiment in the form of a method includes receiving cash state data from an SSTD into an SSTD cash state simulator and applying a set of simulated input demand sequence data to the cash state data to obtain outputs over a simulated period. This method, while executing tracks a simulated cash state of the SSTD from which the SSTD cash state data was received over the simulated period to identify SSTD servicing needs. The method then stores the identified SSTD servicing needs in an SSTD management module.

Abstract: The various embodiments herein each include at least one of systems, methods, and software for discrete-event simulation for transaction service point device cash servicing, such as SSTDs. Such embodiments provide a unique, completely different analytic approach, and predicts a more detailed set of intractable insights for efficient servicing cash needs of SSTDs. One example embodiment in the form of a method includes receiving cash state data from an SSTD into an SSTD cash state simulator and applying a set of simulated input demand sequence data to the cash state data to obtain outputs over a simulated period. This method, while executing tracks a simulated cash state of the SSTD from which the SSTD cash state data was received over the simulated period to identify SSTD servicing needs. The method then stores the identified SSTD servicing needs in an SSTD management module.

Abstract: Various embodiments herein each include at least one of systems, methods, and software for in situ and network-based transaction classification. Such embodiments use advanced data analytics and machine learning techniques of consumer's transaction attributes to reduce shrink at checkout. One embodiment, in the form of a method, includes processing a dataset of transactions to identify normal transaction patterns and processing a dataset of transactions that included known fraud to identify variation patterns between the identified normal transaction patterns and the data of each transaction. The method further includes generating at least one pattern model based on the identified normal transaction patterns and the identified variation patterns. In such embodiments, each pattern model typically includes classification values for determining a likelihood of fraud in transactions.

Abstract: Devices and techniques for cash management of self-service transactional terminals are provided. Cash flow, cash holding cost, and cash service cost data, associated with one or more self-service transactional devices are received. An optimal cash reset value and associated interval between services calls may be calculated based on the cash flow data, the cash holding cost data, and the cash service cost data. The cash reset value being the amount of cash left in each of the one or more self-service transactional devices after a service call.

Abstract: Devices and techniques for cash management of self-service transactional terminals are provided. Cash flow, cash holding cost, and cash service cost data, associated with one or more self-service transactional devices are received. An optimal cash reset value and associated interval between services calls may be calculated based on the cash flow data, the cash holding cost data, and the cash service cost data. The cash reset value being the amount of cash left in each of the one or more self-service transactional devices after a service call.

Abstract: Convenience Store Effectiveness Model (CSEM) is a self-contained PC application to quantitatively predict operational and financial impact of changes to Convenience Store (CStore) and Financial Services Center (FSC) operations. CSEM includes Simulation Analysis Module and Financial Analysis Module. Simulation Analysis Module includes FSC model and CStore model. CStore model predicts the effect of an unlimited number of changes in store design, customer demand patterns, and checkout procedures on store performance. Financial Analysis Module creates a Profit and Loss (P&L) statement showing cash flows, Net Present Value (NPV), and Internal Rate of Return (IRR) for deploying FSCs using simulation results or user input values. An analyst can use CSEM to provide a sound and quantified basis for developing a business case for investing in new technologies, i.e., FSC, or other design and procedure changes in a convenience store environment.

Abstract: The Convenience Store Effectiveness Model (CSEM) is a self-contained PC desktop application enabling an analyst to quantitatively predict the operational and financial impact of changes to Convenience Store (CStore) and Financial Services Center (FSC) operations. This application, according to the present invention, includes a Simulation Analysis Module and a Financial Analysis Module. The Simulation Module consists of two simulation models: FSC model and CStore model. An analyst can use the CStore model to predict the effect of an unlimited number of changes in store design, customer demand patterns, and checkout procedures on store performance. The Financial Analysis Module allows the user to create a Profit and Loss (P&L) statement showing the cash flows, Net Present Value (NPV), Internal Rate of Return (IRR) for deploying FSCs using simulation results or user input values.