Patent Application
20200050972
The present disclosure relates generally to an improved computer system and, in particular, to a method and apparatus for machine learning predictive modeling. Still more particularly, the present disclosure relates to a method and apparatus for predicting employee take home pay in specific industries/sectors and geographic regions.
Many consumers have multiple incomes. They may have multiple jobs and/or combined household incomes. One source of information about income combined from multiple sources is self-reported income on tax returns which may include multiple jobs and joint filings indicating potential access to income from another individual. Combining income sources to quantify total income at the individual level is a complex task and often includes inaccuracies.
Some companies rely on “household” logic to combine individuals into households and attempt to calculate total income for the household. This method is inaccurate because some individuals that reside at the same physical address are not related relative to financial income.
Income is just one component of calculating take home pay. Some individuals with the same salary might have different voluntary payroll deductions for things like retirement plans, health savings accounts, etc., that affect their available cash flow. In addition, some individuals are dependent on others for expenses like lodging, food, clothing, etc. As a result, calculating effective take home pay can be extremely challenging.
Therefore, it would be desirable to have a method and system that provides predictive modeling and indices that predict take home pay and allow comparison across different industries/sectors and geographic regions.
An embodiment of the present disclosure provides a computer-implemented method for predictive modeling. The computer system aggregates payroll data regarding a plurality of factors associated with take home pay and performs iterative analysis on the data using machine learning to construct a predictive model. The computer system then uses the predictive model to populate a database with predicted values of take home pay for selected populations. The computer system converts the predicted values of take home pay in the database into percentages of observed values of take home pay for the selected populations over a specified time period to create indices of take home pay. The computer system then rank orders the selected populations according to their indices of take home pay.
Another embodiment of the present disclosure provides a machine learning predictive modeling system comprising a computer system and one or more processors running on the computer system. The one or more processors aggregate payroll data regarding a plurality of factors associated with take home pay; perform iterative analysis on the data using machine learning to construct a predictive model; populate, using the predictive model, a database with predicted values of take home pay for selected populations; convert the predicted values of take home pay in the database into percentages of observed values of take home pay for the selected populations over a specified time period to create indices of take home pay; and rank order the selected populations according to their indices of take home pay.
Another embodiment of the present disclosure provides a computer program product for machine learning predictive modeling comprising a persistent computer-readable storage media; first program code, stored on the computer-readable storage media, for aggregating payroll data regarding a plurality of factors associated with take home pay; second program code, stored on the computer-readable storage media, for performing iterative analysis on the data using machine learning to construct a predictive model; third program code, stored on the computer-readable storage media, for populating a database with predicted values of take home pay for selected populations; fourth program code, stored on the computer-readable storage media, for converting the predicted values of take home pay in the database into percentages of observed values of take home pay for the selected populations over a specified time period to create indices of take home pay; and fifth program code, stored on the computer-readable storage media, for rank ordering the selected populations according to their indices of take home pay.
The features and functions can be achieved independently in various embodiments of the present disclosure or may be combined in yet other embodiments in which further details can be seen with reference to the following description and drawings.
The novel features believed characteristic of the illustrative embodiments are set forth in the appended claims. The illustrative embodiments, however, as well as a preferred mode of use, further objectives and features thereof, will best be understood by reference to the following detailed description of an illustrative embodiment of the present disclosure when read in conjunction with the accompanying drawings, wherein:
The illustrative embodiments recognize and take into account one or more different considerations. For example, the illustrative embodiments recognize and take into account that it is difficult to accurately predict effective take home pay among individuals that may have significantly different allocations of available income.
The illustrative embodiments further recognize and take into account that people with the same salary might have significantly different take home pay due to differences in factors such as age, payroll deductions, industries/sectors, and geographic regions.
The illustrative embodiments further recognize and take into account that official income is just one component of take home pay and that estimating take home pay based on self-reported income on tax returns and the application of “household” logic is often inaccurate.
Thus, a method and apparatus that would allow for accurately predicting the effective take home pay of employees would fill a long-felt need in the field of employee benefits analysis, institutional lending, and marketing.
The flowcharts and block diagrams in the different depicted embodiments illustrate the architecture, functionality, and operation of some possible implementations of apparatuses and methods in an illustrative embodiment. In this regard, each block in the flowcharts or block diagrams may represent at least one of a module, a segment, a function, or a portion of an operation or step. For example, one or more of the blocks may be implemented as program code.
In some alternative implementations of an illustrative embodiment, the function or functions noted in the blocks may occur out of the order noted in the figures. For example, in some cases, two blocks shown in succession may be performed substantially concurrently, or the blocks may sometimes be performed in the reverse order, depending upon the functionality involved. Also, other blocks may be added, in addition to the illustrated blocks, in a flowchart or block diagram.
As used herein, the phrase “at least one of,” when used with a list of items, means different combinations of one or more of the listed items may be used and only one of each item in the list may be needed. In other words, “at least one of” means any combination of items and number of items may be used from the list, but not all of the items in the list are required. The item may be a particular object, thing, or a category.
For example, without limitation, “at least one of item A, item B, or item C” may include item A, item A and item B, or item B. This example also may include item A, item B, and item C or item B and item C. Of course, any combinations of these items may be present. In some illustrative examples, “at least one of” may be, for example, without limitation, two of item A, one of item B, and ten of item C; four of item B and seven of item C; or other suitable combinations.
With reference now to the figures and, in particular, with reference to
The computer-readable program instructions may also be loaded onto a computer, a programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, a programmable apparatus, or other device to produce a computer implemented process, such that the instructions which execute on the computer, the programmable apparatus, or the other device implement the functions and/or acts specified in the flowchart and/or block diagram block or blocks.
In the depicted example, server computer 104 and server computer 106 connect to network 102 along with storage unit 108. In addition, client computers include client computer 110, client computer 112, and client computer 114. Client computer 110, client computer 112, and client computer 114 connect to network 102. These connections can be wireless or wired connections depending on the implementation. Client computer 110, client computer 112, and client computer 114 may be, for example, personal computers or network computers. In the depicted example, server computer 104 provides information, such as boot files, operating system images, and applications to client computer 110, client computer 112, and client computer 114. Client computer 110, client computer 112, and client computer 114 are clients to server computer 104 in this example. Network data processing system 100 may include additional server computers, client computers, and other devices not shown.
Program code located in network data processing system 100 may be stored on a computer-recordable storage medium and downloaded to a data processing system or other device for use. For example, the program code may be stored on a computer-recordable storage medium on server computer 104 and downloaded to client computer 110 over network 102 for use on client computer 110.
In the depicted example, network data processing system 100 is the Internet with network 102 representing a worldwide collection of networks and gateways that use the Transmission Control Protocol/Internet Protocol (TCP/IP) suite of protocols to communicate with one another. At the heart of the Internet is a backbone of high-speed data communication lines between major nodes or host computers consisting of thousands of commercial, governmental, educational, and other computer systems that route data and messages. Of course, network data processing system 100 also may be implemented as a number of different types of networks, such as, for example, an intranet, a local area network (LAN), or a wide area network (WAN).
The illustration of network data processing system 100 is not meant to limit the manner in which other illustrative embodiments can be implemented. For example, other client computers may be used in addition to or in place of client computer 110, client computer 112, and client computer 114 as depicted in
In the illustrative examples, the hardware may take the form of a circuit system, an integrated circuit, an application-specific integrated circuit (ASIC), a programmable logic device, or some other suitable type of hardware configured to perform a number of operations. With a programmable logic device, the device may be configured to perform the number of operations. The device may be reconfigured at a later time or may be permanently configured to perform the number of operations. Programmable logic devices include, for example, a programmable logic array, programmable array logic, a field programmable logic array, a field programmable gate array, and other suitable hardware devices. Additionally, the processes may be implemented in organic components integrated with inorganic components and may be comprised entirely of organic components, excluding a human being. For example, the processes may be implemented as circuits in organic semiconductors.
Turning to
Computer system 200 comprises information processing unit 216, machine intelligence 218, and indexing program 230. Machine intelligence 218 comprises machine learning 220 and predictive algorithms 222.
Machine intelligence 218 can be implemented using one or more systems such as an artificial intelligence system, a neural network, a Bayesian network, an expert system, a fuzzy logic system, a genetic algorithm, or other suitable types of systems. Machine learning 220 and predictive algorithms 222 may make computer system 200 a special purpose computer for dynamic predictive modelling of take home pay.
In an embodiment, processing unit 216 comprises one or more conventional general purpose central processing units (CPUs). In an alternate embodiment, processing unit 216 comprises one or more graphical processing units (GPUs). Though originally designed to accelerate the creation of images with millions of pixels whose frames need to be continually recalculated to display output in less than a second, GPUs are particularly well suited to machine learning. Their specialized parallel processing architecture allows them to perform many more floating point operations per second then a CPU, on the order of 1000× more. GPUs can be clustered together to run neural networks comprising hundreds of millions of connection nodes.
Indexing program 230 comprises information gathering 252, selecting 232, modeling 234, comparing 236, indexing 238, ranking 240, and displaying 242. Information gathering 252 comprises internal 254. Internal 254 is configured to gather data from internal databases 260.
Thus, processing unit 216, machine intelligence 218, and indexing program 230 transform a computer system into a special purpose computer system as compared to currently available general computer systems that do not have a means to perform machine learning predictive modeling such as computer system 200 of
Turning to
In an illustrative embodiment employee personal data 320 comprises employee age 322 and employee tenure 324. Information regarding employee age statistics is maintained in employee age 322. Information regarding employee tenure is maintained in employee tenure 324.
Financial data 330 contains employee compensation information. Information regarding the employee salaries is maintained in salary 332. Information about the number and amount of deductions is maintained in payroll deductions 334. Information regarding employee tax filing status is maintained in tax forms 336.
Employment data 340 comprises information about an employee's employment. Information regarding the industry/sector in which an employee is employed is maintained in industry/sector 342. A sector identifies a high-level group of related businesses. It can be thought of as a generic type of business. For example, the North American Industry Classification System (NAICS) uses a six digit code to identify an industry. The first two digits of that code identify the sector in which the industry belongs. Information regarding the location of employment is maintained in geographic region 344.
Turning to
It should be emphasized that the specific sequence of steps in the illustrative embodiment shown in
Process 400 begins by determining the amount of money that is on an employee's regular paycheck (step 402). Next the process calculates the total amount of payroll deductions from the base paycheck (step 404). The deductions can include health insurance, dental and vision insurance (both for the employee and/or family members), health savings account, retirement savings, stock purchase plans, dependents and approximate age, and garnishment.
Tax filing status on employee tax forms is used to determine if the employee is the only wage earner in the household (step 406). The age of the employee is then determined (step 408) and the employee's tenure at the place of employment (step 410).
Next the process determines the industry/sector in which the employee is employed (step 412) and the predefined geographic region of employment (e.g., zip code, city, state, multistate region, etc.) (step 414). In cases where the employee works remotely from another region, the employee's region of residence is determined in step 414 from the employee information database.
The method of the present disclosure utilizes machine learning and predictive algorithms such as those provided by machine intelligence 218 in
Turning to
Process 500 begins by aggregating the employee payroll data associated with the factors determined in the process flow in
After the dataset is aggregated, process 500 scrubs the dataset (step 504). Very large datasets, sometimes referred to as Big Data, often contain noise and complicated data structures. Bordering on the order of petabytes, such datasets comprise a variety, volume, and velocity (rate of change) that defies conventional processing and is impossible for a human to process without advanced machine assistance. Scrubbing refers to the process of refining the dataset before using it to build a predictive model and includes modifying and/or removing incomplete data or data with little predictive value. It can also entail converting text based data into numerical values (one-hot encoding) or convert numerical values into a category.
After the dataset has been scrubbed, process 500 divides the data into training data and test data to be used for building and testing the predictive model (step 506). To produce optimal results, the same data that is used to test the model should not be the same data used for training. The data is divided by rows, with 70-80% used for training and 20-30% used for testing. Randomizing the selection of the rows avoids bias in the model.
Process 500 then performs iterative analysis on the training date by applying predictive algorithms to construct a predictive model (step 508). There are three main categories of machine learning: supervised, unsupervised, and reinforcement. Supervised machine learning comprises providing the machine with test data and the correct output value of the data. Referring back to table 600 in
If unsupervised learning is used, not all of the variables and data patterns are labeled, forcing the machine to discover hidden patterns and create labels on its own through the use of unsupervised learning algorithms. Unsupervised learning has the advantage of discovering patterns in the data no one previously knew existed. Examples of algorithms used in unsupervised machine learning include k-means clustering (k-NN), association analysis, and descending clustering.
After the model is constructed, the test data is fed into model to test its accuracy (step 510). In an embodiment the model is tested using mean absolute error, which examines each prediction in the model and provides an average error score for each prediction. If the error rate between the training and test dataset is below a predetermined threshold, the model has learned the dataset's pattern and passed the test.
If the model fails the test the hyperparameters of the model are changed and/or the training and test data are re-randomized, and the iterative analysis of the training data is repeated (step 512). Hyperparameters are the settings of the algorithm that control how fast the model learns patterns and which patterns to identify and analyze. Once a model has passed the test stage it is ready for application.
Whereas supervised and unsupervised learning reach an endpoint after a predictive model is constructed and passes the test in step 510, reinforcement learning continuously improves its model using feedback from application to new empirical data. Algorithms such as Q-learning are used to train the predictive model through continuous learning using measurable performance criteria (discussed in more detail below).
After the model is constructed and tested for accuracy, process 500 uses the model to calculate predicted take home pay, changes in take home pay, as well as other components of take home pay (step 514). Take home pay encompasses a more specific definition than disposable income. Whereas disposable income is typically defined as salary minus taxes, take home pay is a more accurate reflection of how that disposable income is allocated between future and present use. Two people with the same salary might have significantly different take home pay resulting from differences in contributions to retirement accounts, health savings accounts or family health insurance, etc., which affect the residual income available for immediate purchases. These differences in allocation of income can be influenced by a variety of factors such as age and stage of career, as well as socioeconomic factors related to the industry and sector of employment and geographic location.
The predicted values are then converted into a percentage of observed take home pay to form an index (step 516). The index is calculated by dividing the observed value by the predicted value and then multiplying by 100. A percentage greater than 100% identifies employees that have more take home pay than most people with similar characteristics (i.e. lower retirement withholding, insurance, etc.). A percentage less than 100% identifies employees that have less take home pay than most people with similar characteristics (i.e. higher withholding for retirement, insurance, etc.). The indices represent percentiles of the predicted absolute amount of take home pay.
After the indices have been calculated, they are used to rank order industries and/or geographic regions (step 518). Rank ordering facilitates comparison of take home pay across different industries/sectors and geographic areas based on voluntary payroll deductions. Marketing efforts can use this information to help target messages to the correct people. Groups with reduced payroll withholding have more money available for discretionary purchases. Businesses can use this information to help evaluate the benefits they offer employees. Potentially improved benefits could increase employee satisfaction and reduce attrition. Lending institutions can use this information as part of load underwriting criteria. The same verified income from different people does not necessarily mean that they have the same amount of money to pay their debt obligations.
If reinforcement learning is used with the predictive modelling, the take home pay index rankings are compared to the actual observed take home of the industry/sectors and/or regions in question over a subsequent time period (e.g., month, quarter, year, etc.) (step 520). The actual take home of the industry/sectors and/or regions might not conform as expected to their relative index ranking. Furthermore, the sample data used to construct the predictive model might become outdated. Updated payroll data is collected after the subsequent time period and fed back into the machine learning to update and modify the predictive model (step 522).
The illustrative embodiments thus produce the technical effect of constructing accurate, complex predictive models from large datasets and do so in a timely manner in the face of rapidly changing empirical data.
Turning now to
Processor unit 704 serves to execute instructions for software that may be loaded into memory 706. Processor unit 704 may be a number of processors, a multi-processor core, or some other type of processor, depending on the particular implementation. In an embodiment, processor unit 704 comprises one or more conventional general purpose central processing units (CPUs). In an alternate embodiment, processor unit 704 comprises one or more graphical processing units (CPUs).
Memory 706 and persistent storage 708 are examples of storage devices 716. A storage device is any piece of hardware that is capable of storing information, such as, for example, without limitation, at least one of data, program code in functional form, or other suitable information either on a temporary basis, a permanent basis, or both on a temporary basis and a permanent basis. Storage devices 716 may also be referred to as computer-readable storage devices in these illustrative examples. Memory 716, in these examples, may be, for example, a random access memory or any other suitable volatile or non-volatile storage device. Persistent storage 708 may take various forms, depending on the particular implementation.
For example, persistent storage 708 may contain one or more components or devices. For example, persistent storage 708 may be a hard drive, a flash memory, a rewritable optical disk, a rewritable magnetic tape, or some combination of the above. The media used by persistent storage 708 also may be removable. For example, a removable hard drive may be used for persistent storage 708. Communications unit 710, in these illustrative examples, provides for communications with other data processing systems or devices. In these illustrative examples, communications unit 710 is a network interface card.
Input/output unit 712 allows for input and output of data with other devices that may be connected to data processing system 700. For example, input/output unit 712 may provide a connection for user input through at least one of a keyboard, a mouse, or some other suitable input device. Further, input/output unit 712 may send output to a printer. Display 714 provides a mechanism to display information to a user.
Instructions for at least one of the operating system, applications, or programs may be located in storage devices 716, which are in communication with processor unit 704 through communications framework 702. The processes of the different embodiments may be performed by processor unit 704 using computer-implemented instructions, which may be located in a memory, such as memory 706.
These instructions are referred to as program code, computer-usable program code, or computer-readable program code that may be read and executed by a processor in processor unit 704. The program code in the different embodiments may be embodied on different physical or computer-readable storage media, such as memory 706 or persistent storage 708.
Program code 718 is located in a functional form on computer-readable media 720 that is selectively removable and may be loaded onto or transferred to data processing system 600 for execution by processor unit 704. Program code 718 and computer-readable media 720 form computer program product 722 in these illustrative examples. In one example, computer-readable media 720 may be computer-readable storage media 724 or computer-readable signal media 726.
In these illustrative examples, computer-readable storage media 724 is a physical or tangible storage device used to store program code 718 rather than a medium that propagates or transmits program code 718. Alternatively, program code 718 may be transferred to data processing system 700 using computer-readable signal media 726.
Computer-readable signal media 726 may be, for example, a propagated data signal containing program code 718. For example, computer-readable signal media 726 may be at least one of an electromagnetic signal, an optical signal, or any other suitable type of signal. These signals may be transmitted over at least one of communications links, such as wireless communications links, optical fiber cable, coaxial cable, a wire, or any other suitable type of communications link.
The different components illustrated for data processing system 700 are not meant to provide architectural limitations to the manner in which different embodiments may be implemented. The different illustrative embodiments may be implemented in a data processing system including components in addition to or in place of those illustrated for data processing system 700. Other components shown in
The flowcharts and block diagrams in the different depicted embodiments illustrate the architecture, functionality, and operation of some possible implementations of apparatuses and methods in an illustrative embodiment. In this regard, each block in the flowcharts or block diagrams may represent at least one of a module, a segment, a function, or a portion of an operation or step. For example, one or more of the blocks may be implemented as program code.
In some alternative implementations of an illustrative embodiment, the function or functions noted in the blocks may occur out of the order noted in the figures. For example, in some cases, two blocks shown in succession may be performed substantially concurrently, or the blocks may sometimes be performed in the reverse order, depending upon the functionality involved. Also, other blocks may be added in addition to the illustrated blocks in a flowchart or block diagram.
The description of the different illustrative embodiments has been presented for purposes of illustration and description and is not intended to be exhaustive or limited to the embodiments in the form disclosed. The different illustrative examples describe components that perform actions or operations. In an illustrative embodiment, a component may be configured to perform the action or operation described. For example, the component may have a configuration or design for a structure that provides the component an ability to perform the action or operation that is described in the illustrative examples as being performed by the component. Many modifications and variations will be apparent to those of ordinary skill in the art. Further, different illustrative embodiments may provide different features as compared to other desirable embodiments. The embodiment or embodiments selected are chosen and described in order to best explain the principles of the embodiments, the practical application, and to enable others of ordinary skill in the art to understand the disclosure for various embodiments with various modifications as are suited to the particular use contemplated.
