The subject matter described herein relates to various embodiments of a machine learning verification procedure.
Machine learning algorithms and models can be popular for business applications, such as for automating repetitive tasks (e.g., matching deliveries with orders or payments with invoices). Such machine learning models can learn from historic or training data. Some issues can be associated with using some machine learning models. For example, a machine learning model can be dependent on a quality of the training data. For example, special cases that have not occurred in the past may not be correctly solved by the machine learning model. Additional issues can include overfitting or underfitting. For example, in the case of overfitting, the machine learning model may incorrectly match data entries, such as entries that have some similarities but are not a correct match. An example of underfitting may include when a small difference between two data entries results in a non-match when such entries should have been considered a match. Furthermore, over time machine learning algorithms can require re-trainings. However, it can be difficult for users to determine when and if machine learning models require retraining. Such issues can counteract the automation benefits of machine learning and reduce acceptance and trust by users.
This document presents systems, methods, and techniques to verify and calibrate a machine learning model. In one aspect, there is provided a system. The system may include at least one data processor and at least one memory. The at least one memory may store instructions that result in operations when executed by the at least one data processor. The operations may include training a machine learning model by at least processing training data with the machine learning model. The training data may include a plurality of invoice statements and a plurality of payment statements. The machine learning model can be trained to match an invoice statement of the plurality of invoice statements to a corresponding payment statement of the plurality of payment statements. The operations may further include manipulating a first data set of the training data and applying the manipulated first data set to the machine learning model to thereby determine a first matching rate. In addition, the operations may include applying the manipulated first data set to a rule engine to thereby determine a second matching rate and determining a difference between the first matching rate and the second matching rate. Furthermore, the operations may include determining whether the difference is within a predefined threshold range and providing an error indication if the determined difference is outside of the predefined threshold range.
In some variations, one or more features disclosed herein including the following features may optionally be included in any feasible combination. The first matching rate may include a first number of matches between invoice statements of the plurality of invoice statements and payment statements of the plurality of corresponding payment statements within the first data set. The second matching rate may include a second number of matches between invoice statements of the plurality of invoice statements and payment statements of the plurality of corresponding payment statements within the second data set. The predefined threshold range may include an acceptable difference between the first number of matches and the second number of matches. The operations may further include retraining the machine learning model if the determined difference is outside of the predefined threshold range. The manipulating the first data set may include changing at least one parameter of at least one of the invoice statements and the payment statements. The at least one parameter may include one or more of an invoice amount, a payment amount, an invoice number, and a customer name.
In another aspect, there is provided a method including training a machine learning model by at least processing training data with the machine learning model. The training data may include a plurality of invoice statements and a plurality of payment statements. The machine learning model can be trained to match an invoice statement of the plurality of invoice statements to a corresponding payment statement of the plurality of payment statements. The method may further include manipulating a first data set of the training data and applying the manipulated first data set to the machine learning model to thereby determine a first matching rate. In addition, the method may include applying the manipulated first data set to a rule engine to thereby determine a second matching rate and determining a difference between the first matching rate and the second matching rate. Furthermore, the method may include determining whether the difference is within a predefined threshold range and providing an error indication if the determined difference is outside of the predefined threshold range.
In another aspect, there is provided a computer program product that includes a non-transitory computer readable storage medium. The non-transitory computer-readable storage medium may include program code that causes operations when executed by at least one data processor. The operations may include training a machine learning model by at least processing training data with the machine learning model. The training data may include a plurality of invoice statements and a plurality of payment statements. The machine learning model can be trained to match an invoice statement of the plurality of invoice statements to a corresponding payment statement of the plurality of payment statements. The operations may further include manipulating a first data set of the training data and applying the manipulated first data set to the machine learning model to thereby determine a first matching rate. In addition, the operations may include applying the manipulated first data set to a rule engine to thereby determine a second matching rate and determining a difference between the first matching rate and the second matching rate. Furthermore, the operations may include determining whether the difference is within a predefined threshold range and providing an error indication if the determined difference is outside of the predefined threshold range.
Implementations of the current subject matter can include, but are not limited to, methods consistent with the descriptions provided herein as well as articles that comprise a tangibly embodied machine-readable medium operable to cause one or more machines (e.g., computers, etc.) to result in operations implementing one or more of the described features. Similarly, computer systems are also described that may include one or more processors and one or more memories coupled to the one or more processors. A memory, which can include a non-transitory computer-readable or machine-readable storage medium, may include, encode, store, or the like one or more programs that cause one or more processors to perform one or more of the operations described herein. Computer implemented methods consistent with one or more implementations of the current subject matter can be implemented by one or more data processors residing in a single computing system or multiple computing systems. Such multiple computing systems can be connected and can exchange data and/or commands or other instructions or the like via one or more connections, including, for example, to a connection over a network (e.g. the Internet, a wireless wide area network, a local area network, a wide area network, a wired network, or the like), via a direct connection between one or more of the multiple computing systems, etc.
The details of one or more variations of the subject matter described herein are set forth in the accompanying drawings and the description below. Other features and advantages of the subject matter described herein will be apparent from the description and drawings, and from the claims. While certain features of the currently disclosed subject matter are described for illustrative purposes in relation to the prediction of anomalies in the operations of a database, it should be readily understood that such features are not intended to be limiting. The claims that follow this disclosure are intended to define the scope of the protected subject matter.
The accompanying drawings, which are incorporated in and constitute a part of this specification, show certain aspects of the subject matter disclosed herein and, together with the description, help explain some of the principles associated with the disclosed implementations. In the drawings,
When practical, similar reference numbers denote similar structures, features, or elements.
The current subject matter is directed to systems and methods that include a machine learning verification procedure, and that can efficiently and effectively determine an accuracy of a trained machine learning model. In some embodiments, the machine learning verification procedure can provide for relearning of the machine learning model, such as when the machine learning model is found to be inaccurate. For example, the machine learning verification procedure can train a machine learning model, verify whether the machine learning model is working correctly or not, and/or assist with retraining the machine learning model (e.g., when the machine learning model is not working correctly). As such, the machine learning verification procedure can provide an efficient and effective way for users depending on information provided by the machine learning model to know if the machine learning model is working correctly or not. Furthermore, the machine learning verification procedure can provide information to a user regarding how the machine learning model is functioning compared to a standard rule engine, as well as information and/or assistance regarding retraining the machine learning model, as will be described in greater detail below. Various embodiments and features of the machine learning verification procedure are described herein.
In some embodiments, the machine learning model can be trained using training data that includes invoice statements and corresponding payment statements. The machine learning model can be trained to match payment statements with the correct corresponding invoice statements. As such, the trained machine learning model can assist a business with monitoring and managing issued invoices and received payments. However, to ensure that the machine learning model is correctly trained, the machine learning verification of the current subject matter can assist with verifying the effectiveness of the trained machine learning model, such as how accurate the invoice/payment statement matching is being performed. Furthermore, the machine learning verification procedure can assist with retraining the machine learning model, such as by providing an indication related to the inaccuracy of the machine learning model invoice/payment matching and/or assisting with retraining the machine learning model based on the determined inaccuracy of the machine learning model.
As will be described in greater detail below, some embodiments of the machine learning verification procedure include both traditional rule based algorithms and machine learning model to assist with verifying the accuracy of the machine learning model. As such, the machine learning verification procedure described herein can improve customer trust in using machine learning models, such as to assist with running a business, as well as provide an efficient and effective way to validate and calibrate a machine learning model. Various embodiments and examples of the machine learning verification procedure are described in greater detail below. The machine learning verification procedure can include a model, a process, a part of a system, etc., without departing from the scope of this disclosure.
As shown in
The procedure of manipulating the data and applying both the machine learning model and the rules engine can be repeated and the matching rates in both cases can be saved for each iteration. As a result of this process, at least two matching rate curves for the two approaches can be produced (see, for example,
Although the machine learning verification procedure 100 and machine learning model 102 are described herein with regards to matching invoice statements and payment statements, any number of data can be included in the training data. Furthermore, the machine learning verification procedure and machine learning model can perform any number of manipulations, analysis, etc. to such training data without departing from the scope of this disclosure. For example, the machine learning verification procedure can verify the accuracy of any number of machine learning models and assist with retraining the machine learning model, as necessary. Furthermore, the machine learning verification procedure and machine learning model can be include in any number of systems for processing various types and sizes of data.
For example, the machine learning model can match the invoice statement 200 with the payment statement 202, thereby indicating that the invoice shown in
Furthermore,
As shown in
In some embodiments, for every payment-invoice match, only one parameter is changed, e.g. the payment amount is reduced. Once manipulated, the modified data can be saved, such as for further processing. In some embodiments, changes to the data can be recorded to thereby identify what changes were done, which may assist in evaluating results in a later stage.
As shown in
At 606, the manipulated first data set can be applied to a rule engine to thereby determine a second matching rate. At 608, the manipulated first data set can be applied to the machine learning model to thereby determine a first matching rate. In some embodiments, the first matching rate can include a first number of matches between invoice statements of the plurality of invoice statements and payment statements of the plurality of corresponding payment statements within the first data set. In addition, the second matching rate can include a second number of matches between invoice statements of the plurality of invoice statements and payment statements of the plurality of corresponding payment statements within the second data set. In some embodiments, the predefined threshold range can include an acceptable difference between the first number of matches and the second number of matches.
At 610, a difference between the first matching rate and the second matching rate can be determined. At 612, a determination whether the difference is within a predefined threshold range can be made. At 614, an error indication can be provided if the determined difference is outside of the predefined threshold range. In some embodiments, the machine learning verification procedure can further include retraining the machine learning model if the determined difference is outside of the predefined threshold range.
As shown in
The memory 720 is a computer readable medium such as volatile or non-volatile that stores information within the computing system 700. The memory 720 can store data structures representing configuration object databases, for example. The storage device 730 is capable of providing persistent storage for the computing system 700. The storage device 730 can be a floppy disk device, a hard disk device, an optical disk device, or a tape device, or other suitable persistent storage means. The input/output device 740 provides input/output operations for the computing system 700. In some example embodiments, the input/output device 740 includes a keyboard and/or pointing device. In various implementations, the input/output device 740 includes a display unit for displaying graphical user interfaces.
According to some example embodiments, the input/output device 740 can provide input/output operations for a network device. For example, the input/output device 740 can include Ethernet ports or other networking ports to communicate with one or more wired and/or wireless networks (e.g., a local area network (LAN), a wide area network (WAN), the Internet).
In some example embodiments, the computing system 700 can be used to execute various interactive computer software applications that can be used for organization, analysis and/or storage of data in various formats. Alternatively, the computing system 700 can be used to execute any type of software applications. These applications can be used to perform various functionalities, e.g., planning functionalities (e.g., generating, managing, editing of spreadsheet documents, word processing documents, and/or any other objects, etc.), computing functionalities, communications functionalities, etc. The applications can include various add-in functionalities (e.g., SAP Integrated Business Planning as an add-in for a spreadsheet and/or other type of program) or can be standalone computing products and/or functionalities. Upon activation within the applications, the functionalities can be used to generate the user interface provided via the input/output device 740. The user interface can be generated and presented to a user by the computing system 700 (e.g., on a computer screen monitor, etc.).
One or more aspects or features of the subject matter described herein can be realized in digital electronic circuitry, integrated circuitry, specially designed ASICs, field programmable gate arrays (FPGAs) computer hardware, firmware, software, and/or combinations thereof. These various aspects or features can include implementation in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device. The programmable system or computing system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.
These computer programs, which can also be referred to as programs, software, software applications, applications, components, or code, include machine instructions for a programmable processor, and can be implemented in a high-level procedural and/or object-oriented programming language, and/or in assembly/machine language. As used herein, the term “machine-readable medium” refers to any computer program product, apparatus and/or device, such as for example magnetic discs, optical disks, memory, and Programmable Logic Devices (PLDs), used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term “machine-readable signal” refers to any signal used to provide machine instructions and/or data to a programmable processor. The machine-readable medium can store such machine instructions non-transitorily, such as for example as would a non-transient solid-state memory or a magnetic hard drive or any equivalent storage medium. The machine-readable medium can alternatively or additionally store such machine instructions in a transient manner, such as for example, as would a processor cache or other random access memory associated with one or more physical processor cores.
To provide for interaction with a user, one or more aspects or features of the subject matter described herein can be implemented on a computer having a display device, such as for example a cathode ray tube (CRT) or a liquid crystal display (LCD) or a light emitting diode (LED) monitor for displaying information to the user and a keyboard and a pointing device, such as for example a mouse or a trackball, by which the user may provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well. For example, feedback provided to the user can be any form of sensory feedback, such as for example visual feedback, auditory feedback, or tactile feedback; and input from the user may be received in any form, including acoustic, speech, or tactile input. Other possible input devices include touch screens or other touch-sensitive devices such as single or multi-point resistive or capacitive track pads, voice recognition hardware and software, optical scanners, optical pointers, digital image capture devices and associated interpretation software, and the like.
In the descriptions above and in the claims, phrases such as “at least one of” or “one or more of” may occur followed by a conjunctive list of elements or features. The term “and/or” may also occur in a list of two or more elements or features. Unless otherwise implicitly or explicitly contradicted by the context in which it used, such a phrase is intended to mean any of the listed elements or features individually or any of the recited elements or features in combination with any of the other recited elements or features. For example, the phrases “at least one of A and B;” “one or more of A and B;” and “A and/or B” are each intended to mean “A alone, B alone, or A and B together.” A similar interpretation is also intended for lists including three or more items. For example, the phrases “at least one of A, B, and C;” “one or more of A, B, and C;” and “A, B, and/or C” are each intended to mean “A alone, B alone, C alone, A and B together, A and C together, B and C together, or A and B and C together.” Use of the term “based on,” above and in the claims is intended to mean, “based at least in part on,” such that an unrecited feature or element is also permissible.
The subject matter described herein can be embodied in systems, apparatus, methods, and/or articles depending on the desired configuration. The implementations set forth in the foregoing description do not represent all implementations consistent with the subject matter described herein. Instead, they are merely some examples consistent with aspects related to the described subject matter. Although a few variations have been described in detail above, other modifications or additions are possible. In particular, further features and/or variations can be provided in addition to those set forth herein. For example, the implementations described above can be directed to various combinations and subcombinations of the disclosed features and/or combinations and subcombinations of several further features disclosed above. In addition, the logic flows depicted in the accompanying figures and/or described herein do not necessarily require the particular order shown, or sequential order, to achieve desirable results. Other implementations may be within the scope of the following claims.
Number | Name | Date | Kind |
---|---|---|---|
9043738 | Ward | May 2015 | B1 |
9443268 | Kapczynski | Sep 2016 | B1 |
9449281 | Basel | Sep 2016 | B2 |
9973465 | Linkous | May 2018 | B1 |
10033611 | Linkous | Jul 2018 | B1 |
11256732 | Weiss | Feb 2022 | B2 |
11429712 | Ortiz | Aug 2022 | B2 |
20140178084 | Kuo | Jun 2014 | A1 |
20160217406 | Najmi | Jul 2016 | A1 |
20160239813 | Ko | Aug 2016 | A1 |
20180225667 | Wang | Aug 2018 | A1 |
20180239501 | Reddy | Aug 2018 | A1 |
20180247227 | Holtham | Aug 2018 | A1 |
20190005408 | Tolpin | Jan 2019 | A1 |
20190012733 | Gorman | Jan 2019 | A1 |
20190138384 | Nair | May 2019 | A1 |
Number | Date | Country |
---|---|---|
103527769 | Jan 2014 | CN |
101852527 | Jun 2018 | KR |
Number | Date | Country | |
---|---|---|---|
20200184253 A1 | Jun 2020 | US |