SYSTEM AND A METHOD OF DETERMINING PERCENTILE SIGNIFICANCE FOR SERVICES
TECHNICAL FIELD
[001] This disclosure relates generally to significance testing systems, and more particularly to a system and a method of determining percentile significance for services.
BACKGROUND
[002] Unlike manufacturing processes, service industries always have one sided threshold for providing services, as contractual obligations or performance measurements are concerned. Typically, there is always two-sided specification limits or threshold for manufacturing a tangible product. The specification limit/threshold for the tangible product may not be higher or lower than a tolerance limit. Further, it is critical to perform certain benchmark/target tests and comparison tests for the service industries.
[003] Various conventional systems and methods are available for performing significance tests. However, the conventional systems and methods do not perform significance test at a required percentile level. Most of the conventional systems perform rank-based tests or signed rank tests. The conventional systems perform testing at median level that is around 50th percentile which may lead to interferences. Additionally, some of the conventional systems transform continuous metrics into a discrete factor by applying a threshold and deploy other methods like logistic regression.
[004] Therefore, there is a need to develop a system and method of determining significance at customized percentile level for various service industries.
SUMMARY
[005] In one embodiment, a method for determining percentile significance for a plurality of services is disclosed. The method may include extracting a plurality of data sets from a plurality of services. The plurality of data sets may include a plurality of test parameters associated with a plurality of services. The method may further include generating a plurality of test suits based on the plurality of test parameters for each of the plurality of services. Further, the method may include determining a service category based on the plurality of test parameters using an Artificial Intelligence (AI) model to generate the plurality of test suits. The method may further include evaluating percentile for each of the plurality of test suits associated with the plurality of services. The method may further include determining percentile significance for each of the plurality of services.
[006] In another embodiment, a system for determining percentile significance for a plurality of services is disclosed. The system may include a processor and a memory communicatively coupled to the processor. The memory may store processor-executable instructions, which, on execution, may cause the processor to extract a plurality of data sets from a plurality of services. The plurality of data sets may include a plurality of test parameters associated with a plurality of services. The processor-executable instructions, on execution, may further cause the processor to generate a plurality of test suits based on the plurality of test parameters for each of the plurality of services. The processor-executable instructions, on execution, may further cause the processor to determine a service category based on the plurality of test parameters using an Artificial Intelligence (AI) model. The processor-executable instructions, on execution, may further cause the processor evaluate percentile for each of the test suits associated with the plurality of services. The processor-executable instructions, on execution, may further cause the processor to determine percentile significance for each of the plurality of services.
BRIEF DESCRIPTION OF THE DRAWINGS
[007] The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and, together with the description, serve to explain the disclosed principles.
[008] FIG. 1 is a block diagram of a system for determining percentile significance for services, in accordance with some embodiments of the present disclosure.
[009] FIG. 2 is a functional block diagram of various modules within a memory of a significance testing device configured to determine percentile significance for services, in accordance with some embodiments of the present disclosure.
[010] FIG. 3 is a flowchart of a method for determining percentile significance for services, in accordance with some embodiments of the present disclosure.
[011] FIG. 4 is a flowchart of a method for performing significance proportion test, in accordance with some embodiments of the present disclosure.
[001] FIG. 5 is a block diagram of an exemplary computer system for implementing embodiments consistent with the present disclosure.
DETAILED DESCRIPTION
[012] Exemplary embodiments are described with reference to the accompanying drawings. Wherever convenient, the same reference numbers are used throughout the drawings to refer to the same or like parts. While examples and features of disclosed principles are described herein, modifications, adaptations, and other implementations are possible without departing from the spirit and scope of the disclosed embodiments. It is intended that the following detailed description be considered as exemplary only, with the true scope and spirit being indicated by the following claims. Additional illustrative embodiments are listed below.
[013] Referring to FIG. 1, a system 100, for determining percentile significance of services, is illustrated, in accordance with some embodiments of the present disclosure. The system 100 may include a significance testing device 102 with processing capabilities of determining percentile significance for a plurality of services based on a plurality of test parameters associated with the plurality of services. The significance testing device 102 may include an Artificial Intelligence (AI) model to generate test suits or to perform other internal functions. Further, the significance testing device 102 performs a significance test at a desired level of percentile as applicable for a process/domain/function/department. The plurality of services may be provided to end users or consumers or even a Business to Business (B2B) company involved in service delivery. It should be noted that the plurality of services may be provided by service industries 122. Examples of the service industries may include a Banking, Financial Services and Insurance (BFSI) sector, a retail distribution/delivery company, a transportation industry, a BPO/KPO company/subsidiary/a captive unit, a telecom service provider, healthcare providers, and Utilities company.
[001] The significance testing device 102 may include a memory 104, a processor 106, and an input/output unit 108. The input/output unit (I/O) 108 may further include a display 110 and a user interface 112. A user (e.g., a patient) or an administrator may interact with the significance testing device 102 and vice versa through the I/O unit 108. The I/O unit 108 may be responsible for extracting datasets associated with each of the plurality of services provided by the service industries 122, for processing, and in turn displays a processed output. In one embodiment, the processed output may be displayed by the I/O unit 108 via the display 110. The display 110 may be used to display results of analysis performed by the significance testing device 102, to the user. In alternate embodiment, the processed output may be displayed by the external devices 118. By way of another example, the user interface 110 may be used by the user to provide inputs to the significance testing device 102. Thus, for example, in some embodiments, the significance testing device 102 may ingest data provided by administrator via the user interface 112. Further, for example, in some embodiments, the significance testing device 102 may render intermediate results or final results (e.g., percentile significances) to the administrator or the user via the user interface 112. In some embodiments, the user/administrator may provide inputs to the significance testing device 102 via the user interface 112.
[002] The memory 104 may store instructions that, when executed by the processor 106, may cause the processor 106 to determine percentile significance or performing a percentile significance test, in accordance with some embodiments. As will be described in greater detail in conjunction with FIG. 2 and FIG. 3, in order to determine percentile significance, the processor 106 in conjunction with the memory 104 may perform various functions including extracting datasets, generating test suits, determining category, evaluating percentiles, and determining percentile significance.
[003] The memory 104 may also store various data that may be captured, processed, and/or required by the significance testing device 102. The memory 104 may be a non-volatile memory (e.g., flash memory, Read Only Memory (ROM), Programmable ROM (PROM), Erasable PROM (EPROM), Electrically EPROM (EEPROM) memory, etc.) or a volatile memory (e.g., Dynamic Random Access Memory (DRAM), Static Random-Access memory (SRAM), etc.)
[004] Further, the significance testing device 102 may interact with a server 114 or external devices 118 over a network 120 for sending and receiving various data. The external devices 118 may include, but may not be limited to a desktop, a laptop, a notebook, a netbook, a tablet, a smartphone, a remote server, a mobile phone, or another computing system/device. The network 120, for example, may be any wired or wireless communication network and the examples may include, but may be not limited to, the Internet, Wireless Local Area Network (WLAN), Wi-Fi, Long Term Evolution (LTE), Worldwide Interoperability for Microwave Access (WiMAX), and General Packet Radio Service (GPRS).
[014] In some embodiments, the significance testing device 102 may receive information associated with each of the plurality of services from the server 114. The server 114 may be configured to extract a plurality of test parameters associated with each of the plurality of services provided by the service industries 122. The server 112 may further include a database 116, which may store information related to each of the plurality of services on the server 114. Alternatively, an individual (e.g., a service provider, a customer, a user) may access information associated with each of the plurality of services via the external devices 118 coupled with the significance testing device 102 via network 120.
[015] It is apparent to the person skilled in art that the manufacturing processes have two-sided specification limit and service industries have one sided threshold/specification limit as far as performance is concerned. By way of an example, consider a scenario of manufacturing a cap of a bottle, a gear, or a show. In that case, the cap of a bottle, a gear, or a show should not be too tight or too loose to fit in, for being assembled. In contrast, for the service industries, the performance may always be one sided for measuring compliance to the service level commitments.
[016] On the other hand, consider a scenario where a service is associated with the BFSI sector, and a customer applies for a mutual fund redemption. There may be a time limit for the customer to complete the redemption. Also, the customer may complete the redemption complying the time limit. As a result, the amount may be transferred to customer’s account. By way of another example of a telecom or electricity supply corporation, a service restoration/renewal/activation may be expected to be completed within a certain time for certain disruption/new request. This may be an upper limit for completion of the service. For instances, when the service is completed or addressed before the upper limit, no one may be disappointed.
[017] Similarly, for the BPO/KPO industry, Service Level Agreements (SLA) between the service provider and customers may be time bound that may be referred as Turn Around Time (TAT). Further, TAT may be measured for a time duration from time of receiving a request to resolution/completion. Also, upper limits of TAT measure may be reported either monthly or quarterly. For example, 90% of work needs to be completed in 3 days, and 95% needs be completed in 5 days. Although, percentage and time in days/hours may vary. Further, in case of noncompliance, penalty clauses may be applied in terms of percentage of invoiced fees payable.
[018] The significance testing device 102 may be capable of performing a robust percentile significance test at a particular percentile of completion of a service. Detailed explanation of operations to perform a robust percentile significance test is provided further in FIGS. 2-5.
[019] Referring now to FIG. 2, a block diagram of various module within the memory 104 of the significance testing device 102 configured to determine percentile significance for services is illustrated, in accordance with some embodiments of the present disclosure. The memory 104 may include a data extraction module 202, a test suit generation module 204, a percentile evaluation module 206, and a significance determination module 208, and a distribution assumption module 210. The modules 202-210 may perform various functions to perform a percentile significance at particular level of completion of a service request (for example, when SLA indicates that 90% of work for a particular service is completed in 5 days). Further, the memory 104 may also include a database 212 to store various data and intermediate results generated by the modules 202-210.
[020] The significance testing device 102 may perform critical comparison of different work items for a same process, between two shifts, or among other factors. For example, a comparison between debt fund redemption and an equity fund redemption, a comparison of health policy renewals of senior citizens and other citizens. The other factors may include locations or sites. For example, for a global outsourcing company, comparison of Chennai site versus Manila site versus Prague site. The significance test may be a statistical significance test which reduces the chances of wrong inferences and improve business performance. The significance test may be based on sample data. However, extrapolated and computed for the larger sample of scope of work or population for deriving a probability value.
[021] The data extraction module 202 may be configured to extract data sets 216a associated with a plurality of services 216. In particular, the data extraction module 202 may extract the data sets 216a from the plurality of services 216 provided by the service industries 214 (Similar to the service industries 122). The service industries 214 may belong to at least one of a BFSI sector, a retail distribution/ a delivery company, a transportation industry, a BPO/KPO company/subsidiary/a captive unit, a telecom service provider, healthcare providers, and a Utility company. The data sets may include a plurality of test parameters. For example, the plurality of test parameters may include, but is not limited to, sample items, cycle time for each item, a benchmark value of cycle time, hypothesized proportion, a relation with benchmark, and an alpha value or level of significance. Further, the data extraction module 202 may be connected to the test suit generation module 204 and the database 212.
[022] The test suit generation module 204 may be configured generate test suits for each of the plurality of services. The test suits may be generated based on the plurality of parameters. Further, the test suit generation module 204 employs a category determination model 204a. The category determination model 204a may determine a service category. In some embodiments, the category determination model 204a may correspond to an AI model. The test suit generation module 204 may be communicatively coupled to the percentile evaluation module 206 and the database 212. The percentile evaluation module 206 may be configured to evaluate percentile of service completion for each of the test suits associated with the plurality of services. This may be explained in detail in conjunction with FIG. 3. The percentile evaluation module 206 may be connected to the database 212 for storing and retrieving various data. Also, the percentile evaluation module 206 may be operatively connected to the significance determination module 208 to process the generated output.
[023] The significance determination module 208 may be configured to determine significance at predefined percentiles for each of the plurality of services. The significance determination module 208 may continuously communicate with the percentile evaluation module 206 to identify percentile of work completion for each of the plurality of services. Further, the significance determination module 208 may also be operatively connected to the distribution assumption module 210. The distribution assumption module 210 may involve distribution assumptions, like normal distribution, bernoulli’s distribution, poisson distribution, binomial distribution etc. Further, results generated by the significance determination module 208 may be provided to a user.
[024] It should be noted that all such aforementioned modules 202 – 210 may be represented as a single module or a combination of different modules. Further, as will be appreciated by those skilled in the art, each of the modules 202 – 210 may reside, in whole or in parts, on one device or multiple devices in communication with each other. In some embodiments, each of the modules 202 – 210 may be implemented as dedicated hardware circuit comprising custom application-specific integrated circuit (ASIC) or gate arrays, off-the-shelf semiconductors such as logic chips, transistors, or other discrete components. Each of the modules 202 – 210 may also be implemented in a programmable hardware device such as a field programmable gate array (FPGA), programmable array logic, programmable logic device, and so forth. Alternatively, each of the modules 202 – 210 may be implemented in software for execution by various types of processors (e.g., processor 106). An identified module of executable code may, for instance, include one or more physical or logical blocks of computer instructions which may, for instance, be organized as an object, procedure, function, or other construct. Nevertheless, the executables of an identified module or component need not be physically located together but may include disparate instructions stored in different locations which, when joined logically together, include the module and achieve the stated purpose of the module. Indeed, a module of executable code could be a single instruction, or many instructions, and may even be distributed over several different code segments, among different applications, and across several memory devices.
[025] Referring now to Fig. 3, a method for determining percentile significance for services is depicted via a flowchart 300, in accordance with some embodiments of the present disclosure. Each step of the flowchart 300 may be performed by various modules 202-210 of the significance testing device 102. It should be noted that the FIG. 3 is explained in conjunction with FIG. 2.
[026] At step 302, data sets (similar to the data sets 216a) may be extracted from a plurality of services (for example, the services 216) provided by service industries (analogous to the service industries 214). The data sets may be extracted by the data extraction module 202. In some embodiments, the plurality of services may be provided by a single service industry. In some other embodiments, the plurality of services may be provided multiple service industries belonging to different sectors. The service industries may belong to at least one of a BFSI sector, a retail distribution/ a delivery company, a transportation industry, a BPO/KPO company/subsidiary/a captive unit, a telecom service provider, healthcare providers, and a Utility company. Further, in some embodiments a critical benchmark/target test and a comparison test for sustaining quality on an ongoing basis in the above-mentioned service industries may be performed. Further, the data sets may include a plurality of test parameters associated with the plurality of services. For example, the plurality of test parameters may include, but is not limited to, sample items, cycle time for each item, a benchmark value of cycle time, hypothesized proportion, a relation with benchmark, and an alpha value or level of significance.
[027] At step 304, test suits may be generated based on the plurality of test parameters for each of the plurality of services. It should be noted that the test suits may be generated by test suit generation module 204. In some embodiments, a service category may be determined to identify association among the plurality of test parameters and the plurality of services. Thereafter, at step 306, percentiles may be evaluated for each of the test suits associated with the plurality of services. In some embodiments, percentile of service completion may be evaluated. For example, the significance testing device 102 may evaluate completion of work in percentile (such as, 90% or 95% work is completed) for a particular service, in a particular time. For percentile evaluation, the significance testing device 102 may employ the percentile evaluation module 206. At step 308, percentile significance may be determined for each of the plurality of services. In some embodiments, significance test may be performed at a configured percentile of completion of work that may vary based on requirement. In some embodiments, the significance test may involve distribution assumptions, like normal distribution, bernoulli’s distribution, poisson distribution, binomial distribution etc.
[028] By way of an example, consider an equation y=f(x). In this equation ‘y’ is a function of ‘x’. If a user wants to check significance impact of a plurality machines at a particular percentile of each item’s cycle time, then alternative hypothesis as cycle time percentile = f (machines) may be considered. This means a particular percentile of cycle time is significantly impacted by the plurality of machines. In such case, user entries (test parameters) may include sample data (x): single column having discrete data of two levels, sample data (y): single column having continuous data, and percentile value: float value (i.e., between 0 and 1).
[029] Further, an assumed hypothesis may be a “Null Hypothesis”. In the null hypothesis, ‘x’ column may have no significant impact at percentile value of the ‘y’ column. In alternative hypothesis, ‘x’ column may have significant impact at given percentile value of the ‘y’ column. And, an output may include a contingency table, an odds ratio, and a ‘p’ value.
[030] Further, in one example, a single column of discrete values may be passed. The single column may have two levels that may be treated as ‘x’ variable (i.e., two types of machines). Another single column may have continuous variable ‘y’ (i.e., cycle time of the sample items), and a percentile value at which user wants to check significant impact of the ‘x’ variable. Further, in some embodiments, a percentile value of the ‘y’ column may be determined which may be used as a cutoff value. Values greater than or equal to the percentile value may be coded as “greater_equal_percentile” and other values as “smaller_percentile”.
[031] In some embodiments, a contingency table of the coded “greater_equal_percentile” and “smaller_percentile, and given two levels of x column may be created. Moreover, in some embodiments, fisher's exact test to the contingency table may be applied. Finally, it may return the contingency table, odds ratio, and ‘p’ value of the fisher's exact test.
[032] For example, if the user wants to find machines’ (i.e., machine A’s and machine B’s) significant impact on 70th percentile of cycle time. In this case, a function give below may be used:
bhargab (x=df ["MACHINE"], y=df ["cycle_time (DAYS)"], percentile=0.7)
[033] Null hypothesis “H0” may be “machine has no significant impact at 70th percentile of productivity”. Alternative hypothesis “Ha” may be “machine has significant impact at 70th percentile of productivity”. If the ‘p’ value is more than 0.05, null hypothesis may be accepted. This is further explained in detail in conjunction with FIG. 4.
[034] Referring now to Fig. 4, a method for performing significance proportion test is depicted via a flowchart 400, in accordance with some embodiments of the present disclosure. Each step of the method may be performed using the significance testing device 102. FIG. 4 is explained in conjunction with FIGS. 2 and 3. In the method, items, each item’s cycle time, a benchmark value of cycle time, hypothesized proportion (i.e., the minimum proportion value of total items), a relation with benchmark (for example, benchmark is greater than or less than), an alpha value (i.e., 0.05) may be passed, and an output including a ‘p’ value, a ‘z’ score, and confidence interval (CI) range may be received. The CI range may be upper and lower end of confidence Interval range and may represent whether the population of the sample has less than or greater than that hypothesized percentage of items which are greater or less than that value (i.e., selected by the relation). In some embodiments, the method may be used for variables like productivity in production industry, and delivery time for online shopping platforms.
[035] At step 402, various parameters including a data column, a benchmark, a hypothesized proportion value, a relation, and an alpha value (i.e., level of significance which may be default value ‘0.05’) may be processed through the significance testing device 102. At step 404, a condition of relation equal to grater may be checked. if the condition is true, step 406a may be executed. Otherwise, step 406b of the process may be executed. At step 406a, values which are greater than or equal to the benchmark may be transformed as "pass" and at step 406b, other values may be transformed as "fail".
[036] Further, at step 408, a contingency table of "fail" and "pass" may be created. At step 410, benchmark value may be compared with maximum value of the data. For example, if benchmark value is less than, greater than, or equal to the maximum value of the data or not may be checked. Thereafter, at step 412, one sample proportion test may be performed. If benchmark value is less than the maximum value of the data then a sample proportion test may be performed on number of count of "pass" from the contingency table, sum of count of both “pass” and “fail” as total number of trials, hypothesized proportion which has been passed in the function as value of one sample proportion test and alternative for one sample proportion test is smaller, and get the range of confidence interval (CI) of the one sample test on the basis of alpha value passed in the function. Otherwise, when benchmark is greater than maximum value of the data passed, one sample proportion test may be performed on number of count of "pass" as zero (0), sum of count of “fail” as total number of trials because there may be no “pass” as the benchmark greater than maximum value of the data passed, hypothesized proportion value which has been passed in the function as value of one sample proportion test and alternative for the one sample proportion test is smaller, and get the range of confidence interval of the one sample test on the basis of alpha value passed in the function.
[037] Therefore, null hypothesis of the proportion test may be “proportion of "pass" in population is greater or equal to the hypothesized proportion”. Alternative hypothesis of the proportion test may be “proportion of "pass" in population is smaller than the hypothesized proportion”. As the value greater than or equal to the benchmark is defined as "pass". so final hypothesis for the total function may be:
H0 (i.e., a null hypothesis): “proportion of data greater than or equal to the benchmark value (in population) is greater than or equal to the hypothesized pro portion (percentage benchmark)”, and
Ha (i.e., alternative hypothesis): “proportion of data greater than or equal to the benchmark (value) in population is smaller than the hypothesized proportion (percentage benchmark)”.
As a result, z statistics of that one sample proportion test, p value of that one sample proportion test, and range of CI may be received.
[038] In one example, consider that data has two columns of machine type and productivity. The machine type may be ‘A1’ to ‘A5’, and corresponding productivities may be 334, 377, 397, 304, and 305. Now, when a user wants to check 90% of machines have productivity more than or equal to 350 unit or not. Then a function give below may be used:
Prop(data=df2[“productivity”], value=350, proportion=0.9, relation= “greater”
H0 (null hypothesis): Proportion of productivity more than or equal to 350 unit is greater than or equal to 90%, and
Ha (alternative hypothesis): Proportion of productivity more than or equal to 350 units is less than 90%.
[039] In this case the p-value may be less than 0.05 (as alpha value is by default 0.05). So, an alternative hypothesis of this test may be accepted. As mentioned before that this function may be used for cycle time of items in service industries also. For this, a function may be run by selecting relation as smaller. And, for this, else if part of the function may be conducted.
[040] Further, if user entries relation = "smaller", then the values which are less than or equal to the benchmark may be coded as "pass" and others may be coded as "fail". Thereafter, a contingency table of "fail" and "pass" may be created. If benchmark value is greater than or equal to the minimum value of the data, then one sample proportion test may be performed on number of counts of "pass" (from the contingency table), sum of count of both “pass” and “fail” as total number of trials, hypothesized proportion (which has been passed in the function) as value of one sample proportion test and alternative for one sample proportion test is smaller. Also, the range of confidence interval (CI) of the one sample test may be calculated based on alpha value passed in the function. Otherwise (i.e., when benchmark is less than minimum value of the data passed), test one sample proportion test may be performed on number of count of "pass" as zero (0), sum of count of “fail” as total number of trials (because there will be no “pass” as the benchmark is less than minimum value of the data passed), hypothesized proportion value (which has been passed in the function) as value of one sample proportion test and alternative for the one sample proportion test is smaller. Also, the range of CI of the one sample test may be calculated on the basis of alpha value passed in the function, thus:
Null hypothesis of proportion test: Proportion of "pass" in population is greater or equal to the hypothesized proportion (percentage benchmark), and
Alternative hypothesis of proportion test: Proportion of "pass" in population is smaller than the hypothesized proportion (percentage benchmark).
[041] Further, z statistics of that one sample proportion test, p value of that one sample proportion test, and range of CI may be determined. So, final hypothesis for the total function may be:
H0 (null hypothesis): Proportion of data less than or equal to the benchmark in population is greater than or equal to the hypothesized proportion, and
Ha (alternative hypothesis): Proportion of data less than or equal to the benchmark in population is smaller than the hypothesized proportion.
[042] The z statistics of that one sample proportion test, p value of that one sample proportion test, and range of confidence interval may be determined.
[043] In another example, data may have two columns. One column is for item number, and another is for cycle time. Now, if a user wants to check 80% of items are done before or within 4 units or not. Then a function given below may be used:
Prop (data=df ["cycle_time"], value=4, proportion=0.8, relation="smaller", alpha=0.05)
H0 (null hypothesis): Proportion of items completed before or within 4 units is greater than or equal to 80%, and
Ha (alternative hypothesis): Proportion of items completed before or within 4 units is less than 80%.
Here, the ‘p’ value may be more than 0.05 as alpha value is by default 0.05. Therefore, in this case, a null hypothesis may be accepted.
[044] The disclosed system and methods may overcome drawbacks of conventional techniques. The service industries may use the disclosed system to perform a significance test at a required percentile according to process performance criteria. The disclosed system provides accurate results as compared to other tests at various percentile, as the system utilized internally a combination of proportion distribution around a particular percentile, and then uses exact Fisher’s test. The disclosed method is stochastic and extrapolates decision for a larger sample or population specific for continuous data at any given percentile.
[045] The disclosed methods and systems may be implemented on a conventional or a general-purpose computer system, such as a personal computer (PC) or server computer. Referring now to FIG. 5, an exemplary computing system 500 that may be employed to implement processing functionality for various embodiments (e.g., as a SIMD device, client device, server device, one or more processors, or the like) is illustrated. Those skilled in the relevant art will also recognize how to implement the invention using other computer systems or architectures. The computing system 500 may represent, for example, a user device such as a desktop, a laptop, a mobile phone, personal entertainment device, DVR, and so on, or any other type of special or general-purpose computing device as may be desirable or appropriate for a given application or environment. The computing system 500 may include one or more processors, such as a processor 502 that may be implemented using a general or special purpose processing engine such as, for example, a microprocessor, microcontroller or other control logic. In this example, the processor 502 is connected to a bus 504 or other communication medium. In some embodiments, the processor 502 may be an Artificial Intelligence (AI) processor, which may be implemented as a Tensor Processing Unit (TPU), or a graphical processor unit, or a custom programmable solution Field-Programmable Gate Array (FPGA).
[046] The computing system 500 may also include a memory 506 (main memory), for example, Random Access Memory (RAM) or other dynamic memory, for storing information and instructions to be executed by the processor 502. The memory 506 also may be used for storing temporary variables or other intermediate information during execution of instructions to be executed by the processor 502. The computing system 500 may likewise include a read only memory (“ROM”) or other static storage device coupled to bus 504 for storing static information and instructions for the processor 502.
[047] The computing system 500 may also include storage devices 508, which may include, for example, a media drive 510 and a removable storage interface. The media drive 510 may include a drive or other mechanism to support fixed or removable storage media, such as a hard disk drive, a floppy disk drive, a magnetic tape drive, an SD card port, a USB port, a micro USB, an optical disk drive, a CD or DVD drive (R or RW), or other removable or fixed media drive. A storage media 512 may include, for example, a hard disk, magnetic tape, flash drive, or other fixed or removable medium that is read by and written to by the media drive 510. As these examples illustrate, the storage media 512 may include a computer-readable storage medium having stored therein particular computer software or data.
[048] In alternative embodiments, the storage devices 508 may include other similar instrumentalities for allowing computer programs or other instructions or data to be loaded into the computing system 500. Such instrumentalities may include, for example, a removable storage unit 514 and a storage unit interface 516, such as a program cartridge and cartridge interface, a removable memory (for example, a flash memory or other removable memory module) and memory slot, and other removable storage units and interfaces that allow software and data to be transferred from the removable storage unit 514 to the computing system 500.
[049] The computing system 500 may also include a communications interface 518. The communications interface 518 may be used to allow software and data to be transferred between the computing system 500 and external devices. Examples of the communications interface 518 may include a network interface (such as an Ethernet or other NIC card), a communications port (such as for example, a USB port, a micro USB port), Near field Communication (NFC), etc. Software and data transferred via the communications interface 518 are in the form of signals which may be electronic, electromagnetic, optical, or other signals capable of being received by the communications interface 518. These signals are provided to the communications interface 518 via a channel 520. The channel 520 may carry signals and may be implemented using a wireless medium, wire or cable, fiber optics, or other communications medium. Some examples of the channel 520 may include a phone line, a cellular phone link, an RF link, a Bluetooth link, a network interface, a local or wide area network, and other communications channels.
[050] The computing system 500 may further include Input/Output (I/O) devices 522. Examples may include, but are not limited to a display, keypad, microphone, audio speakers, vibrating motor, LED lights, etc. The I/O devices 522 may receive input from a user and also display an output of the computation performed by the processor 502. In this document, the terms “computer program product” and “computer-readable medium” may be used generally to refer to media such as, for example, the memory 506, the storage devices 508, the removable storage unit 514, or signal(s) on the channel 520. These and other forms of computer-readable media may be involved in providing one or more sequences of one or more instructions to the processor 502 for execution. Such instructions, generally referred to as “computer program code” (which may be grouped in the form of computer programs or other groupings), when executed, enable the computing system 500 to perform features or functions of embodiments of the present invention.
[051] In an embodiment where the elements are implemented using software, the software may be stored in a computer-readable medium and loaded into the computing system 500 using, for example, the removable storage unit 514, the media drive 510 or the communications interface 518. The control logic (in this example, software instructions or computer program code), when executed by the processor 502, causes the processor 502 to perform the functions of the invention as described herein.
[052] It is intended that the disclosure and examples be considered as exemplary only.

We Claim:

1. A method (300) for determining percentile significance for a plurality of services, the method (300) comprising:
extracting (302), by a significance testing device (102), a plurality of data sets from the plurality of services, wherein the plurality of data sets comprises a plurality of test parameters associated with the plurality of services;
generating (304), by the significance testing device (102), a plurality of test suits based on the plurality of test parameters for each of the plurality of services, wherein generating the plurality of test suits comprises determining (304a) a service category based on the plurality of test parameters using an Artificial Intelligence (AI) model;
evaluating (306), by the significance testing device (102), percentile for each of the plurality of test suits associated with the plurality of services; and
determining (308), by the significance testing device (102), percentile significance for each of the plurality of services.

2. The method (300) of claim 1, wherein determining (304a) the service category comprises determining association among the plurality of test parameters and the plurality of services.

3. The method (300) of claim 1, wherein the plurality of services is provided by at least one of plurality of service industries.

4. The method (300) of claim 3, wherein the plurality of service industries comprises a Banking, Financial Services and Insurance (BFSI) sector, a retail distribution/ a delivery company, a transportation industry, a BPO/KPO company/subsidiary/a captive unit, a telecom service provider, healthcare providers, and a utility company.

5. The method (300) of claim 1, wherein the plurality of test parameters comprises sample items, cycle time for each item, a benchmark value of cycle time, hypothesized proportion, a relation with benchmark, and an alpha value or level of significance.

6. A system (100) for determining percentile significance for a plurality of services comprising:
a processor (106); and
a memory (104) communicatively coupled to the processor (106), wherein the memory (104) stores processor-executable instructions, which, on execution, causes the processor (106) to:
extract (302) a plurality of data sets from a plurality of services, wherein the plurality of data sets comprises a plurality of test parameters associated with a plurality of services;
generate (304) a plurality of test suits based on the plurality of test parameters for each of the plurality of services, wherein generating (304a) the plurality of test suits further comprises determining a service category based on the plurality of test parameters using an Artificial Intelligence (AI) model;
evaluate (306) percentile for each of the test suits associated with the plurality of services; and
determine (308) percentile significance for each of the plurality of services.

7. The system (100) of claim 6, wherein the processor-executable instructions cause the processor (106) to determine the service category by determining association among the plurality of test parameters and the plurality of services.

8. The system (100) of claim 6, wherein the plurality of services is provided by at least one of plurality of service industries.

9. The system (100) of claim 8, wherein the plurality of service industries comprises a Banking, Financial Services and Insurance (BFSI) sector, a retail distribution/ a delivery company, a transportation industry, a BPO/KPO company/subsidiary/a captive unit, a telecom service provider, healthcare providers, and a Utility company.

10. The system (100) of claim 6, wherein the plurality of test parameters comprises sample items, cycle time for each item, a benchmark value of cycle time, hypothesized proportion, a relation with benchmark, and an alpha value or level of significance.