Claims:We Claim:

1. An electronic system for forecasting a recurring economic event, the electronic system including a server comprising:
a processor and a memory configured to store computer-readable instructions, wherein when the instructions are executed, the processor performs steps comprising:
identifying a past reference time period during which the economic event has occurred;
collecting, from a transaction database, reference transaction data for a time period preceding the reference time period;
developing a computational model correlating the economic event and reference transaction data;
collecting, from the transaction database, current transaction data for a current time period; and
executing the computational model with the current transaction data to generate a forecast data output,
wherein the forecast data output comprises a probability of the economic event occurring within a future time period.

2. The electronic system according to claim 1, the steps further comprising obtaining past data on economic indicators for the reference time period.

3. The electronic system according to claim 2, wherein the computational model correlates the reference transaction data and past economic indicators data.

4. The electronic system according to claim 3, wherein the forecast data output further comprises forecast data on economic indicators for the future time period.

5. The electronic system according to any one of claims 1 to 4, the steps further comprising collecting, from the transaction database, reference transaction data for a time period succeeding the reference time period.

6. The electronic system according to claim 5, wherein the computational model correlates the reference transaction data for the preceding and succeeding time periods with a start and an end, respectively, of the economic event in the reference time period.
7. The electronic system according to any one of claims 1 to 6, wherein each of the reference and current transaction data comprises a number of transaction parameters.
8. The electronic system according to claim 7, wherein the transaction parameters comprise a merchant category and an expenditure amount.

9. The electronic system according to claim 8, wherein the computational model weights the transaction parameters based on the merchant category.

10. A computerized method implemented on a server for forecasting a recurring economic event, the method comprising:
identifying a past reference time period during which the economic event has occurred;
collecting, from a transaction database, reference transaction data for a time period preceding the reference time period;
developing a computational model correlating the economic event and reference transaction data;
collecting, from the transaction database, current transaction data for a current time period; and
executing the computational model with the current transaction data to generate a forecast data output,
wherein the forecast data output comprises a probability of the economic event occurring within a future time period.

Dated this 19th day of January, 2017

R. Ramya Rao
IN/PA-1607
Of K & S Partners
Agent for the Applicant

, Description:Technical Field

[0001] The present disclosure generally relates to an electronic system and method for forecasting economic events. More particularly, the present disclosure describes various embodiments of an electronic system and method for forecasting a recurring economic event, i.e. an economic event that has occurred at least once before and may potentially occur again in future.

Background

[0002] Economies experience economic or business cycles over time. An economy may be defined with respect to a specific country, geographic region, and/or industry. An economic cycle or business cycle is the natural fluctuation of the economy between stages / periods / phases of steady state / stagnation, expansion / growth, and contraction / recession. Various factors can help to determine the current stage or state of the economic cycle, such as gross domestic product (GDP), interest rates, employment levels, and consumer spending. Generally, the economic cycle has a number of stages – primarily an expansion / growth / boom / upturn stage and a contraction / recession / collapse / downturn stage. Each of these stages may also be referred to as an economic event. Particularly, some economic events may be recurring as economies may have experienced economic cycles before and similar economic events may likely occur again in future.

[0003] Consumers and businesses behave differently to different economic events during the economic cycle. For example, there may be increased spending if the economy is experiencing an economic expansion event, and conversely there may be decreased spending if the economy is experiencing an economic contraction event. However, consumers and businesses tend to behave reactively, i.e. they only act according to the current economic state and as such may not have strategically planned sufficiently ahead of the current economic state.

[0004] Therefore, in order to address or alleviate at least the aforementioned problem / disadvantage, there is a need to provide an electronic system and method for forecasting economic events, in which there is at least one improved feature over the aforementioned prior art.

Summary

[0005] According to an aspect of the present disclosure, there is an electronic system, a computerized method implemented on a server of the electronic system, and a non-transitory computer-readable medium storing computer-readable instructions for forecasting a recurring economic event. Steps of the method comprise: identifying a past reference time period during which the economic event has occurred; collecting, from a transaction database, reference transaction data for a time period preceding the reference time period; developing a computational model correlating the economic event and reference transaction data; collecting, from the transaction database, current transaction data for a current time period; and executing the computational model with the current transaction data to generate a forecast data output, wherein the forecast data output comprises a probability of the economic event occurring within a future time period.

[0006] An electronic system and method for forecasting a recurring economic event according to the present disclosure is thus disclosed herein. Various features, aspects, and advantages of the present disclosure will become more apparent from the following detailed description of the embodiments of the present disclosure, by way of non-limiting examples only, along with the accompanying drawings.

Brief Description of the Drawings

[0007] FIG. 1 is an illustration of an electronic system for implementation of a method for forecasting a recurring economic event, in accordance with an embodiment of the present disclosure.

[0008] FIG. 2A is an illustration of modules / components of a server of the electronic system of FIG. 1, in accordance with an embodiment of the present disclosure.

[0009] FIG. 2B is a block diagram illustration of the technical architecture of the server, in accordance with an embodiment of the present disclosure.

[0010] FIG. 3 is a flowchart illustration of a computerized method for forecasting a recurring economic event, in accordance with an embodiment of the present disclosure.

[0011] FIG. 4 is an illustration of a timeline with various time periods, in accordance with an embodiment of the present disclosure.

[0012] FIG. 5 is an illustration of another timeline with various time periods, in accordance with another embodiment of the present disclosure.

Detailed Description

Overview

[0013] The system includes a server configured for forecasting a recurring economic event, e.g. expansion or recession. The server firstly identifies, e.g. by an identification module or component of the server, a past reference time period during which the economic event has occurred. This past reference time period may be known beforehand or verified based on past data on economic indicators for the reference time period. The server then collects, e.g. by the data collection module or component of the server and from a transaction database, reference transaction data for a time period preceding the reference time period. The reference transaction data includes details of transactions, e.g. purchases made by customers with merchants, performed through a payment network which processes payments for the transactions. This provides data for the server to deduce or infer the transactions that occurred before the economic event happened. The server then develops, e.g. by the computational development module or component of the server, a computational model correlating the economic event and reference transaction data. The computational model can be developed based on statistical data from the reference transaction data using known techniques and models such as time series, predictive, and/or logistic regression models. If there is a correlation between transaction data in one time period and an economic event occurring in the subsequent time period, the computational model can be used to forecast a similar economic event in future if there is transaction data for the current time period. The server then proceeds to collect, e.g. by the data collection module, current transaction data for the current time period. With the current transaction data, the server can execute, e.g. by the computational model, e.g. by an execution or performance module or component of the server, the computational model with the current transaction data to forecast a probability of a similar economic event occurring in future.

[0014] An advantage of the above aspect of the present disclosure is that a user can forecast an economic event, such as an economic recession, based at least on past transaction data. The forecast data output would provide the user with an indication of whether the economic recession is likely to occur in the near future. If there is a strong likelihood, consumer and business activities could be strategically planned in a manner so as to be prepared for the economic recession.

Description of Embodiments

[0015] In the present disclosure, depiction of a given element or consideration or use of a particular element number in a particular figure or a reference thereto in corresponding descriptive material can encompass the same, an equivalent, or an analogous element or element number identified in another figure or descriptive material associated therewith. The use of “/” in a figure or associated text is understood to mean “and/or” unless otherwise indicated. For purposes of brevity and clarity, descriptions of embodiments of the present disclosure are directed to an electronic system and method for forecasting a recurring economic event, in accordance with the drawings. While aspects of the present disclosure will be described in conjunction with the embodiments provided herein, it will be understood that they are not intended to limit the present disclosure to these embodiments. On the contrary, the present disclosure is intended to cover alternatives, modifications and equivalents to the embodiments described herein, which are included within the scope of the present disclosure as defined by the appended claims. Furthermore, in the following detailed description, specific details are set forth in order to provide a thorough understanding of the present disclosure. However, it will be recognized by an individual having ordinary skill in the art, i.e. a skilled person, that the present disclosure may be practiced without specific details, and/or with multiple details arising from combinations of aspects of particular embodiments. In a number of instances, known systems, methods, procedures, and components have not been described in detail so as to not unnecessarily obscure aspects of the embodiments of the present disclosure.

[0016] In representative or exemplary embodiments of the present disclosure, there is provided an electronic system 10 as illustrated in FIG. 1. The electronic system 10 includes a computer or host server 100 configured for executing a method 200 for forecasting a recurring economic event. An economic event may be defined as occurring at a particular point in time, or across a period of time. The economic event may relate to a specific stage or phase of the economic cycle, e.g. a time or period of economic expansion / growth, economic contraction / recession, or economic stagnation / steady-state economy. The economic event may further relate to other aspects of the economy, such as times or periods of inflation or deflation and the magnitude or extent thereof. It will be appreciated that an economic event may relate to and/or is indicative of any aspect or state of the economy. It will also be appreciated that the economic may be on a national scale (for a particular country only), at a regional scale (across multiple countries), or relevant to a specific industry / industries.

[0017] As mentioned above with reference to FIG. 2A, the server 100 includes the identification module 100a for identifying a past reference time period during which the economic event has occurred, a data collection module 100b for collecting reference transaction data for a time period preceding the reference time period and collecting current transaction data for a current time period, a computational development module 100c for developing a computational model correlating the economic event and reference transaction data, and an execution or performance module 100d for executing the computational model with the current transaction data to generate a forecast data output. In addition, FIG. 2B illustrates a block diagram showing a technical architecture of the server 100.

The technical architecture of the server 100 of the electronic system 10 is described as follows with reference to the block diagram shown in FIG. 2B. The technical architecture includes a processor 102 (which may be referred to as a central processor unit or CPU) that is in communication with memory or memory devices including secondary storage 104 (such as disk drives or memory cards), read-only memory (ROM) 106, and random access memory (RAM) 108. The processor 102 may be implemented as one or more CPU chips. The various modules 100a-d are configured as part of the processor 102 for performing various operations or steps of the method 200 in response to non-transitory instructions operative or executed by the processor 102.

[0018] The technical architecture further includes input/output (I/O) devices 110, and network connectivity devices 112. The secondary storage 104 typically includes a memory card or other storage device and is used for non-volatile storage of data and as an over-flow data storage device if RAM 108 is not large enough to hold all working data. Secondary storage 104 may be used to store programs which are loaded into RAM 108 when such programs are selected for execution.

[0019] The secondary storage 104 has a processing component 114, including non-transitory computer-readable instructions operative by the processor 102 to perform various operations of the method 200 according to various embodiments of the present disclosure. The ROM 106 is used to store instructions and perhaps data which are read during program execution. The secondary storage 104, the ROM 106, and/or the RAM 108 may be referred to in some contexts as computer-readable storage media and/or non-transitory computer-readable media. Non-transitory computer-readable media include all computer-readable media, with the sole exception being a transitory propagating signal per se.

[0020] The I/O devices 110 may include printers, video monitors, liquid crystal displays (LCDs), plasma displays, touch screen displays, keyboards, keypads, switches, dials, mice, track balls, voice recognizers, card readers, paper tape readers, and/or other known input devices.

[0021] The network connectivity devices 112 may take the form of modems, modem banks, Ethernet cards, universal serial bus (USB) interface cards, serial interfaces, token ring cards, fibre distributed data interface (FDDI) cards, wireless local area network (WLAN) cards, radio transceiver cards that promote radio communications using protocols such as code division multiple access (CDMA), global system for mobile communications (GSM), long-term evolution (LTE), worldwide interoperability for microwave access (WiMAX), near field communications (NFC), radio frequency identity (RFID), and/or other air interface protocol radio transceiver cards, and other known network devices. These network connectivity devices 112 may enable the processor 102 to communicate with the Internet or one or more intranets. With such a network connection, it is contemplated that the processor 102 might receive information from the network, or might output information to the network in the course of performing the operations or steps of the method 200. Such information, which is often represented as a sequence of instructions to be executed using processor 102, may be received from and outputted to the network, for example, in the form of a computer data signal embodied in a carrier wave.

[0022] The processor 102 executes instructions, codes, computer programs, scripts which it accesses from hard disk, floppy disk, optical disk (these various disk based systems may all be considered secondary storage 104), flash drive, ROM 106, RAM 108, or the network connectivity devices 112. While only one processor 102 is shown, multiple processors may be present. Thus, while instructions may be discussed as executed by a processor, the instructions may be executed simultaneously, serially, or otherwise executed by one or multiple processors.

[0023] It will be appreciated that the technical architecture of the server 100 may be formed by one computer, or multiple computers in communication with each other that collaborate to perform a task. For example, but not by way of limitation, an application may be partitioned in such a way as to permit concurrent and/or parallel processing of the instructions of the application by one computer. Alternatively, the data processed by the application may be partitioned in such a way as to permit concurrent and/or parallel processing of different portions of a data set by the multiple computers. In an embodiment, virtualization software may be employed by the technical architecture to provide the functionality of a number of servers that is not directly bound to the number of computers in the technical architecture. In an embodiment, the functionality disclosed above may be provided by executing the application and/or applications in a cloud computing environment. Cloud computing may include providing computing services via a network connection using dynamically scalable computing resources. A cloud computing environment may be established by an enterprise and/or may be hired on an as-needed basis from a third party provider.

[0024] It is understood that by programming and/or loading executable instructions onto the technical architecture of the server 100, at least one of the CPU 102, the ROM 106, and the RAM 108 are changed, transforming the technical architecture in part into a specific purpose machine or apparatus having the functionality as taught by various embodiments of the present disclosure. It is fundamental to the electrical engineering and software engineering arts that functionality that can be implemented by loading executable software into a computer can be converted to a hardware implementation by known design rules.

[0025] Referring back to FIG. 1, the electronic system 10 further includes a transaction database 20 and data sources 30. The transaction database 20 is communicatively linked to a payment network 40 which processes payments for transactions. The transaction database 20 may form part of or be communicatively connected / linked to the server 100, or the transaction database 20 may reside on a remote server of the electronic system 10.

[0026] The transaction database 20 is configured for recording and storing transaction data or details of transactions performed through the payment network 40 which processes payments for the transactions. The transactions include purchases made by customers with merchants, particularly via electronic or digital payments (e.g. with credit / debit cards) through the payment network 40. The transaction details or data include or relate to a number of transaction parameters or variables associated with the transactions. In some embodiments, the transaction parameters include, but are not limited to, a merchant category and an expenditure amount. For example, for a particular purchase transaction between a customer and a merchant, the transaction parameters includes a merchant category and an expenditure amount. The merchant category includes or is represented by a merchant category code (MCC) that is assigned to the merchant based on its type of business or industry. The expenditure amount refers to the spending paid by the customer to the merchant for the purchase. Some other transaction parameters include the merchant location, date, and time of the transaction.

[0027] The data sources 30 is connected or linked to the server 100. The data sources 30 are sources of data or information relevant to the economy. This economic data may be available in the public domain, or confidentially withheld unless specifically requested for, such as through government / ministerial / official channels. The data sources 30 include journals, newspapers, articles, research papers, government / ministerial / official websites or publications, online portals, etc. Further, the data sources 30 may be available offline and/or online. For offline data sources, a user may be required to manually input or enter the economic data into the server 100. For online data sources, they may be communicatively linked to the server 100 such that the server 100 is able to obtain economic data therefrom. The economic data from the data sources 30 includes, but is not limited to, data on economic indicators or indices, such as GDP, interest rates, employment levels, inflation levels, investments, exports, imports, stock indices, and consumer spending or consumption.

[0028] A statistical module or software 50 may be operative on the server 100 for developing / generating statistical or computational models 60 based on existing statistics or data. Alternatively, the development / generation of the computational models may be performed by the statistical module 50 that is operative remotely from the server 100. The statistics / data may be obtained or derived from the transaction database 20 and/or data sources 30. The statistical module 50 performs statistical analyses of the statistics / data to develop the computational models 60, which may further be based on time series, predictive, and/or logistic regression models.

[0029] With reference to FIG. 3, there is a computer-implemented or computerized method 200, i.e. implemented on a server 100, for forecasting a recurring economic event. As described above, some economic events may be recurring as economies may have experienced economic cycles before and similar economic events may likely occur again in future. In various embodiments of the present disclosure, the method 200 includes:
a step 202 of identifying, e.g. by the identification module or component 100a of the server 100, a past reference time period during which the economic event has occurred;
a step 204 of collecting, e.g. by the data collection module or component 100b of the server 100, from a transaction database 20, reference transaction data for a time period preceding the reference time period;
a step 206 of developing, e.g. by the computational development module or component 100c of the server 100, a computational model 60 correlating the economic event and reference transaction data;
a step 208 of collecting, e.g. by the data collection module 100b, from the transaction database 20, current transaction data for a current time period; and
a step 210 of executing, e.g. by the execution or performance module or component 100d of the server 100, the computational model 60 with the current transaction data to generate a forecast data output.

[0030] The forecast data output includes a probability of the economic event occurring within a future time period. The method 200 may thus be used to forecast or predict a recurring economic event particularly if a same or similar economic event has happened before, such as periods of economic boom or recession. For example, it may be known that the year 2008 is a period of economic recession and the year 2011 is a period of economic boom.

[0031] With reference to a timeline TL1 shown in FIG. 4, the step 202 identifies a past reference time period T1 during which the economic event has occurred. For example, if a user is attempting to forecast an economic recession, a past economic recession would have happened during the reference time period T1. Depending on the type of recurring economic events to forecast, business judgment, and intention of the user, the user may identify or define different reference time periods T1 in the step 202. In some embodiments, the method 200 further includes a step of obtaining, such as from the data sources 30, past data on economic indicators for the reference time period T1. This past data, e.g. GDP and inflation level, may offer additional insights or evidence on the state of the economy during the reference time period T1, and may help to quantify certain traits or characteristics of an economic recession (or more broadly, any economic event).

[0032] A time period T2 preceding or before the reference time period T1 is then defined. The preceding time period T2 may have the same duration as the reference time period T1, or a different duration depending on the business judgment and intention of the user. Further, the reference time period T1 may begin immediately after the end of the preceding time period T2, or there may be a time gap in-between. In the step 204, the server 100 collects reference transaction data from the transaction database 20 for the preceding time period T2. Specifically, the reference transaction data includes details on all or a majority of transactions that were performed during the preceding time period T2. The reference transaction data allows the server 100 to derive collective data such as but not limited to total spending, frequency of spending, average spending per transaction, and average spending across one or more industries. Further, from the reference transaction data, transaction or economic trends may be identified for establishing or developing a framework, i.e. for developing or generating the computational model 60 in the step 206.

[0033] A time period T3 succeeding or after the reference time period T1 may be defined. Similarly, the succeeding time period T3 may have the same duration as the reference time period T1 and/or preceding time period T2, or a different duration depending on the business judgment and intention of the user. Further, the succeeding time period T3 may begin immediately after the end of the reference time period T1, or there may be a time gap in-between. In some embodiments, the method 200 further includes a step of collecting, from the transaction database 20, reference transaction data for the succeeding time period T3. The reference transaction data includes details on all or a majority of transactions that were performed during the succeeding time period T3. Optionally, the method 200 further includes a step of collecting, from the transaction database 20, reference transaction data for the reference time period T1. The reference transaction data includes details on all or a majority of transactions that were performed during the reference time period T1.

[0034] After collecting the reference transaction data for the preceding time period T2 and optionally for the succeeding time period T3 and/or reference time period T1, the method 200 proceeds to the step 206 of developing the computational model 60 with the statistical module 50. The computational model 60 may establish a relationship or correlation between the economic event that happened during the reference time period T1 and the reference transaction data from the preceding time period T2. For example, if the economic event is an economic recession, the reference transaction data from the preceding time period T2 may be indicative of the economic recession that happened later, i.e. during the reference time period T1.

[0035] More specifically, the computational model 60 may establish a relationship or correlation between the economic event in the reference time period T1 and various transaction parameters from the reference transaction data. The computational model 60 may be programmed to generate a forecast data output based on inputs from the transaction parameters, e.g. the forecast data output may be a mathematical function of the transaction parameters.

[0036] One example of such mathematical function is in the following form.
P(X) = A + B*X1 + C*X2 + D*X3
P(X): Probability of the economic event occurring in future
A, B, C, and D: Numerical constants
X1: Transaction parameter of expenditure amount or total spending in the retail industry
X2: Transaction parameter of expenditure amount or total spending in the insurance industry
X3: Transaction parameter of expenditure amount or total spending in the real estate industry

[0037] The mathematical function for calculating P(X) can be expanded to include more transaction parameters X4, X5, or Xn in general, each of which is associated with a distinct industry. The calculated value of P(X) will be more accurate if there are more transaction parameters X to take into account a larger number of industries. The calculated value of P(X) will be more accurate if there is more reference transaction data for each transaction parameter X, i.e. more datasets from a larger number of transactions.

[0038] In one embodiment, the numerical constants are arbitrarily defined during development of the computational model 60. The numerical constants function as variable weightings for the transaction parameters, such as if one or more transaction parameters are more significant than others. For example, the computational model 60 may weigh the transaction parameters based on the merchant category.

[0039] It will be appreciated that the exemplary mathematical function may involve different or other transaction parameters, depending on the business judgment and intention of the user. It will also be appreciated that other forms of mathematical functions, e.g. involving polynomials, logarithms, and/or exponentials, for the computational model 60 may be developed based on analyses of the past reference transaction data.

[0040] In another embodiment, in addition or alternative to the mathematical function, trends during the reference time period (i.e. reference trends) for the respective industries are determined based on the reference transaction data of the transaction parameters X. With the current transaction data for the current time period, trends during the current time period (i.e. current trends) can be determined. For the respective industries, the current trends are matched to the reference trends to determine whether they match and the level or percentage of match. Further, if there is a likely match, the current trend data may be expanded to include current transaction data from earlier than the current time period, i.e. for an increased current time period, to validate the current trends. The current time period may be increased incrementally to further validate the current trends. The current trends would be considered to match the reference trends if the current time period increased until a predetermined threshold duration and/or a predetermined level of match is achieved. The forecast data output is then generated accordingly.

[0041] Referring back to the mathematical function for calculating P(X), using the past economic recession during the reference time period T1 as an example for the computational model 60, the transaction parameters X according to their industry or merchant category are derived from the reference transaction data from the preceding time period T2. The forecast data output includes the probability P(X) which has a value from 0 to 1. If the value of P(X) is closer to 0, the likelihood of an economic recession occurring in future is lower, and if the value of P(X) is closer to 1, the likelihood of an economic recession occurring in future is higher. As it is known that an economic recession indeed occurred during the reference time period T1, the value of P(X) calculated from the transaction parameters X1, X2, and X3 from the preceding time period T2 would be close to 1. Similar transaction parameters for a current time period may be applied to the computational model 60 for forecasting an economic recession.

[0042] In the step 208, the server 100 collects, from the transaction database 20, the current transaction data for a current time period T4. The current time period T4 refers to the most recent time period from the present time. Similarly, the current time period T4 may have the same duration as the reference time period T1 and/or preceding time period T2, or a different duration depending on the business judgment and intention of the user.

[0043] In the step 210, the server 100 executes, operates, or runs the computational model 60 with the current transaction data to generate the forecast data output. The forecast data output includes a probability of the economic event occurring within a future time period T5. Similar to the reference transaction data, the current transaction data includes a number of transaction parameters for input into the computational model 60. The probability P(X) may then be computed and the value of P(X) will provide an indication of the likelihood of the economic event occurring in the future time period T5. Further, the future time period T5 may begin immediately after the end of the current time period T4, or there may be a time gap in-between.

[0044] Comparing with the example of the economic recession in the reference time period T1, the future time period T5 is analogous to the reference time period T1, and the current time period T4 is analogous to the preceding time period T2. Thus, the relationship or correlation established by the computational model 60 based on the reference transaction data for the preceding time period T2 can be used to forecast an economic recession based on the current transaction data for the current time period T4. If the value of P(X) is closer to 0, the likelihood of the economic recession occurring in the future time period T5 is lower, and if the value of P(X) is closer to 1, the likelihood of an economic recession occurring in the future time period T5 is higher. It may also be inferred that, if the value of P(X) is closer to 1, the economic recession may start earlier in the future time period T5.

[0045] In some embodiments, the server 100 may obtain past economic indicators data for the reference time period T1. During development or generation of the computational model 60 in the step 206, the computational model 60 may additionally correlate the reference transaction data and past economic indicators data. Additionally or alternatively, the server 100 may collect reference transaction data for the succeeding time period T3. With the reference transaction data for the preceding time period T2 and succeeding time period T3, the computational model 60 may correlate the reference transaction data for the preceding time period T2 with a start of the economic event in the reference time period T1, and may correlate the reference transaction data for the succeeding time period T3 with an end of the economic event in the reference time period T1.

[0046] In some embodiments, the forecast data output further includes forecast data on economic indicators within the future time period T5. As the past economic indicators data is known for the reference time period T1, the forecast economic indicators data for the future time period T5 may be predicted by the computational model 60. If an economic recession is likely to occur in the future time period T5 based on the probability P(X), it would be advantageously to predict quantified data for certain economic indicators, such as the possible GDP and inflation level during the economic recession. The forecasted quantified data would be more useful for consumers and businesses to strategically plan ahead before the economic recession occurs in the future time period T5.

[0047] The computational model 60 may correlate the reference transaction data for the preceding time period T2 and succeeding time period T3 with the start and end, respectively, of the economic event in the reference time period T1. The computational model 60 may thus be used to forecast the start and end of an economic event. In one example, if there is no economic recession at the present time, the computational model 60 may forecast or estimate the start of the economic recession in future, e.g. in the future time period T5, based on the current transaction data from the current time period T4. In another example, if there is an ongoing economic recession, e.g. occurring in the current time period T4, the computational model 60 may forecast or estimate the end of the economic recession based on the current transaction data from the current time period T4. Predicting the start and end of economic events, particularly economic recessions, may help businesses to strategically plan their investments, as well as government ministries / agencies to formulate public / financial / economic policies.

[0048] In some embodiments with reference to a timeline TL2 shown in FIG. 5, the method 200 may additionally include a step of identifying another past reference time period T6 during which another economic event has occurred. Particularly, the economic event in the reference time period T6 is opposite of the economic event in the reference time period T1. Following on from previous examples, if there is an economic recession in the reference time period T1, then an economic expansion or growth may have happened in the reference time period T6. As described above, an economic expansion would naturally follow an economic recession in an economic cycle. The method 200 may further include a step of obtaining past data on economic indicators from the data sources 30 for the reference time period T6.

[0049] A time period T7 preceding or before the reference time period T6 may be defined, similar to the preceding time period T2 for the reference time period T1. In addition, a time period T8 succeeding or after the reference time period T6 may be defined, similar to the succeeding time period T3 for the reference time period T1. The method 200 may further include a step of collecting reference transaction data from the transaction database 20 for the preceding time period T7 and succeeding time period T8.

[0050] During development or generation of the computational model 60 in the step 206, comparisons / relationships / correlations of the economic indicators data and/or reference transaction data may be made between the economic recession in the reference time period T1 and the economic expansion in the reference time period T6. The computational model 60 could yield evidence on the traits or characteristics of an economic recession / expansion and the differences from each other. The computational model 60 may thus become more effective in forecasting an economic event happening in the future time period T5, whether for an economic expansion or economic recession.

[0051] It will be appreciated that the computational model 60 would be continuously or continually updated with reference transaction data and/or economic indicators data for various aspects of the economy. Particularly, the computational model 60 would be updated with new data when an economic event recurs or a new economic event occurs. Execution of the computational model 60, i.e. the step 210, may be repeated as necessary in attempts to forecast or predict economic events. In addition, the duration of any one or more of the time periods T1 to T8 may be adjusted during development of the computational model 60 to obtain the best-fit model with the available statistical data, such as to discard outliers which may introduce errors into the computational model 60.

[0052] The method 200 advantageously allows a user to forecast an economic event, particularly an economic recession, based on past transaction data and optionally past economic indicators data. The forecast data output would provide the user with an estimated probability of the economic recession happening in the near future or within a future time period. If this probability is high, consumer and business activities could be strategically planned in a manner so as to be prepared for an economic recession. By use of the method 200, specifically the computational model 60, insights on the current and future state of economy may be gained. Warning signals / triggers may be detected early so that there is sufficient time to prepare and plan for changes in the economy, potentially lessening the impact of a severe economic event, particularly a severe or prolonged recession.

[0053] Business entities such as financial institutions, credit card issuers, banks, commercial merchants, and private equity firms, would want to know the current state of economy and the future direction of economy, as well as any signs or triggers which may suggest an economic recession or boom. Such business entities may be able to effectively plan their strategy, marketing, and/or risk management activities based on the direction in which the economy is headed. Individual consumers may also plan their investments based on the current and future state of the economy. Risk-averse consumers may reduce or avoid investments in financial products or stock markets if there are signs of an incoming economic recession. Knowing the current and future state of the economy may also be useful for governments to plan and formulate public / financial / economic policies and/or implement austerity measures which may in turn affect and influence the behavior of consumers and businesses.

[0054] In the foregoing detailed description, embodiments of the present disclosure in relation to an electronic system and method for forecasting a recurring economic event are described with reference to the provided figures. The description of the various embodiments herein is not intended to call out or be limited only to specific or particular representations of the present disclosure, but merely to illustrate non-limiting examples of the present disclosure. The present disclosure serves to address at least one of the mentioned problems and issues associated with the prior art. Although only some embodiments of the present disclosure are disclosed herein, it will be apparent to a person having ordinary skill in the art in view of this disclosure that a variety of changes and/or modifications can be made to the disclosed embodiments without departing from the scope of the present disclosure. Therefore, the scope of the disclosure as well as the scope of the following claims is not limited to embodiments described herein.