Database construction using data extraction for measuring data anomaly impacts

A computing system comprising:

• (a) a computing device having at least one processor;
• (b) a communication interface communicatively coupled to the at least one processor;
• (c) a memory device that stores executable code that, when executed, causes the at least one processor to:
• (i) link to a remote multi-function platform to capture exchange data over a specified window, wherein the exchange data is converted to a standardized format;
• (ii) construct a virtual database that comprises simulated exchange data created using the converted exchange data, wherein an exchange outline software module generates the simulated exchange data;
• (iii) iteratively train, using training data, a machine-learning software module to generate the simulated exchange data, wherein the machine-learning software module is configured with a support vector machine network architecture;
• (iv) insert the training data into an iterative training and testing loop to predict a target variable;
• (v) repeatedly determining, during each iteration of the training and testing loop, the target variable, wherein each iteration of the training and testing loop has differing weights assigned to one or more nodes of the one or more machine learning software modules, each of the differing weights being updated with each iteration of the training and testing loop to reduce error in predicting the target variable and improve predictability of the machine learning software module;
• (vi) deploying the machine learning software modules, and
• (vii) construct the virtual database using the machine learning software module.

A computing system comprising:

• (a) a computing device having at least one processor;
• (b) a communication interface communicatively coupled to the at least one processor;
• (c) a memory device that stores executable code that, when executed, causes the at least one processor to:
• (i) link to a remote multi-function platform to capture exchange data over a specified window, wherein the exchange data is converted to a standardized format;
• (ii) construct a virtual database that comprises simulated exchange data created using the converted exchange data, wherein an exchange outline software module generates the simulated exchange data and the exchange outline software module is comprised of a support vector machine network architecture or CNN network architecture;
• (iii) incorporate a data anomaly within the virtual database;
• (iv) apply a reserve threshold to the virtual database to determine whether the reserve threshold is exceeded;
• (v) generate a reserve threshold signal that is transmitted to an end user computing device and rendered on a display screen as a display element through the communication interface, wherein
• 1. if the reserve threshold signal is not exceeded, the reserve threshold signal has a positive polarity, wherein the reserve threshold signal is represented by the colors green or yellow, and
• 2. if the reserve threshold is not exceeded, the reserve threshold signal has a negative polarity, wherein the reserve threshold signal is represented by the colors red or orange;
• and
• (d) a machine-learning software module and training data, wherein the processor performs the further operations of:
• (i) iteratively training, using the training data, the machine-learning software module to generate simulated exchange data;
• (ii) inserting the training data into an iterative training and testing loop to predict a target variable;
• (iii) repeatedly determining, during each iteration of the training and testing loop, the target variable, wherein each iteration of the training and testing loop has differing weights assigned to one or more nodes of the one or more machine learning software modules, each of the differing weights being updated with each iteration of the training and testing loop to reduce error in predicting the target variable and improve predictability of the machine learning software module;
• (iv) deploying the machine learning software module, and
• (v) executing the simulation using the machine learning software module.