Claims:1. A system for an intelligent cross platform marketing resource optimization comprising:
a meta technology abstraction layer (MTAL), wherein the MTAL is provided in a central application server connected to a plurality of dedicated servers;
a plurality of third party platforms (TPP), wherein the plurality of third party platforms comprises a demand side platform (DSP), a data management platform (DMP) and a plurality of utility platforms, wherein each third party platform is situated in the dedicated server; and
an interface module, wherein the interface module is an intermediatory interface between the MTAL and the plurality of third party platforms.
2. The system as claimed in claim 1, wherein the MTAL comprises:
an analytical module, wherein the analytical module is connected to the plurality of third party platforms for collecting data pertaining to a plurality marketing parameters;
a trafficking module, wherein the trafficking module is connected to plurality of client servers;
a trigger module, wherein the trigger module is connected to the analytical module and comprises a threshold database;
a recommendation engine, wherein the recommendation engine is connected to the trigger module and the analytical module, wherein the recommendation engine comprises a processing unit connected to the analytical module;
an optimizer, wherein the optimizer is connected to the recommendation engine and the plurality of third party platforms; and
a predictor, wherein the predictor is connected to the analytical module, the recommendation engine and the optimizer.
3. The system as claimed in claim 2, wherein the analytical module comprises a channel level key performance indicator (KPI) and a system level KPI, wherein the analytical module gathers a performance data from each TPP for each campaign through the channel level KPI, wherein the analytical module gathers a cross-platform performance data from the plurality of TPPs through the system level KPI.
4. The system as claimed in claim 2, wherein the analytical module has a dynamic graph generation engine to convert a performance data into a numerical value and represent a plurality of collated performance data from a plurality of TPPS into a dynamically evolving graph (DEG) charted against time.
5. The system as claimed in claim 4, wherein the trigger module comprises a mapping engine connected to the graph generation engine, wherein the mapping engine comprises a mapping table with a dynamical updation mechanism, wherein the mapping table list the performance data of each TPP side by side.
6. The system as claimed in claim 5, wherein the threshold database comprises an optimal value of each performance data and is listed in the mapping the engine as a reference value, wherein a constant fluctuation of data below the reference value calculated over a predetermined time frame creates a performance trigger.
7. The system as claimed in claim 6, wherein the predetermined time frame is dynamic in nature depending on a nature of a marketing campaign and a historical performance of the TPP for said marketing campaign, wherein the predetermined time frame ranges from 5-15 days.
8. The system as claimed in claim 7, wherein the recommendation engine creates a rule based recommendation for optimizing a marketing resource comprising primarily but not limited to a campaign bid value and an expenditure on a campaign for each TPP, wherein the recommendation is delivered to a user through a user interface.
9. A computer implemented method for an intelligent cross platform marketing resource optimization comprising:
a) trafficking a marketing campaign through a meta technology abstraction layer (MTAL) to a plurality of third party platform (TPP);
b) setting the campaign’s bid value and expenditure for each TPP;
c) tracking a plurality of key performance indicators (KPI) at a channel level as well as a system level;
d) tracing a dynamic mapping table for the KPI values and comparing each KPI value with a reference value pre-saved in the dynamic mapping table;
e) triggering a performance degradation for at least one TPP and sending the data of KPIs to the recommendation engine;
f) generating a plurality of rule based suggestions list and presenting the suggestions list to a user over a user interface of a client computing device;
g) recording an action of the user on the suggestion list and performing an optimization across the TPPs on the basis of the action by the user;
h) tracking a performance of the campaign after the recorded action and reperforming steps (c)-(g).
10. The method as claimed in claim 9, wherein the channel level KPI comprises cost per thousand impressions (CPM), cost per visit (CPV), cost per impression (CPI), cost per action (CPA) and cost per click (CPC) based on a historical data over the TPP.
11. The method as claimed in claim 9, wherein the system level KPI comprises a primary objective, a secondary objective, an overall budget, impressions, reach and a campaign goal, wherein the primary objective comprises cost per thousand impressions (CPM), cost per visit (CPV), cost per impression (CPI), cost per action (CPA) and cost per click (CPC), wherein the secondary objective comprises click through rate (CTR%), Video Completion Rate (VCR%) , number of leads (lead flow in a designated time period) and a view through rate (VTR%).
12. The method as claimed in claim 9, wherein the optimization comprises a performance classification of the TPPs, a bid change, a bidding algorithm change, a cross channel expenditure budget movement, a budget increase and decrease for a campaign over a TPP, a placement change and a targeting adjustment.
, Description:A) TECHNICAL FIELD
[001] The present invention generally relates to a marketing resource optimization system and particularly relates to a system and method for an intelligent cross platform marketing resource optimization allowing a user to distribute a marketing budget with a better return on investment strategy.

B) BACKGROUND OF INVENTION
[002] A significant and robust market exists for marketing digital advertisements on various types of personal computing devices, like computers (desktop and laptop), mobile phones and tablets, and traditional browser-based devices operated by a consumer who is the user of the device. Conventional advertisement tracking systems and methods which were built for personal devices rely on device identification systems and methods to create a record in buyer advertising systems representing showing a digital advertisement (“ad”) to a consumer (the “impression”), and on which personal device a consumer, who was exposed to the impression, took some action (the “event”) in response to the impression (e.g., visiting a website, making an online purchase, calling a telephone number in response to the advertisement, to name a few.). These impressions and events are monitored to derive data like a efficiency of platform and quality of advertisement as well as a various other analytical points.
[003] Many prior art developments attempted to better the experience of an advertiser through implementation of the aforesaid monitored data. One of such prior arts discloses a system and method include a customer engagement platform of an enterprise. The customer engagement platform is configured to connect with an audience computer and provide to the audience computer contact information associated with a marketing attribution. The marketing attribution accompanies an impression served to the audience computer. The impression and marketing attribution associated with the contact information are sent to the customer engagement platform during an interaction with the enterprise. Various similar prior arts exist in current market to exploit user interaction and platform performance data for enhancing the advertiser experience.
[004] However, the conventional prior art techniques limit a data monitoring on a single platform and hence marketing optimization is limited to a single platform and such marketing optimization are in efficient due to lack relative bias and cross platform monitoring as well as optimization.
[005] In the view of foregoing, there is a need for a system and method for an intelligent cross platform marketing optimization and driving a recommendation engine for an advertiser to improve an advertising experience on at least one online platform.
[006] The above-mentioned shortcomings, disadvantages and problems are addressed herein, as detailed below.

C) OBJECT OF INVENTION
[007] The primary objective of the present invention is to provide a system and method for an intelligent cross platform marketing resource optimization.
[008] Another objective of the present invention is to provide a hierarchical monitoring mechanism that tracks development of one or more advertisements on a platform and parameters related to platform performance.
[009] Yet another objective of the present is to provide holistic channel agnostic media optimization engine through provision of a meta optimization layer function above a plurality of demand side platform (DSP) layers.
[0010] These and other objects and advantages of the embodiments herein will become readily apparent from the following detailed description taken in conjunction with the accompanying drawings.

D) SUMMARY OF INVENTION
[0011] The various embodiments of the present invention provide a system for an intelligent cross platform marketing resource optimization. The system comprises a meta technology abstraction layer (MTAL), a plurality of third party platforms (TPP) and an interface module. The MTAL is provided in a central application server connected to a plurality of dedicated servers. The plurality of third party platforms comprises a demand side platform (DSP), a data management platform (DMP) and a plurality of utility platforms. Each third party platform is situated in the dedicated server. The interface module is an intermediatory interface between the MTAL and the plurality of third party platforms. The interface module is primarily but not limited to a marketing application programming interface (API).
[0012] According to one embodiment of the present invention, the MTAL comprises an analytical module, a trafficking module, a trigger module, a recommendation engine, an optimizer and a predictor. The analytical module is connected to the plurality of third party platforms for collecting data pertaining to a plurality of marketing parameters. The trafficking module is connected to plurality of client servers. The trigger module is connected to the analytical module and comprises a threshold database. The recommendation engine is connected to the trigger module and the analytical module. The recommendation engine comprises a processing unit connected to the analytical module. The optimizer is connected to the recommendation engine and the plurality of third party platforms. The predictor is connected to the analytical module, the recommendation engine and the optimizer.
[0013] According to one embodiment of the present invention, the analytical module comprises a channel level key performance indicator (KPI) and a system level KPI. The analytical module gathers a performance data from each TPP for each campaign through the channel level KPI. The analytical module gathers a cross-platform performance data from the plurality of TPPs through the system level KPI.
[0014] According to one embodiment of the present invention, the analytical module has a dynamic graph generation engine to convert a performance data into a numerical value and represent a plurality of collated performance data from a plurality of TPPS into a dynamically evolving graph (DEG) charted against time.
[0015] According to one embodiment of the present invention, the trigger module comprises a mapping engine connected to the graph generation engine. The mapping engine comprises a mapping table with a dynamical updation mechanism. The mapping table list the performance data of each TPP side by side.
[0016] According to one embodiment of the present invention, the threshold database comprises an optimal value of each performance data and is listed in the mapping the engine as a reference value. A constant fluctuation of data below the reference value calculated over a predetermined time frame creates a performance trigger.
[0017] According to one embodiment of the present invention, the predetermined time frame is dynamic in nature depending on a nature of a marketing campaign and a historical performance of the TPP for said marketing campaign. The predetermined time frame ranges from 5-15 days.
[0018] According to one embodiment of the present invention, the recommendation engine creates a rule based recommendation for optimizing a marketing resource comprising primarily but not limited to a campaign bid value and an expenditure on a campaign for each TPP. The recommendation is delivered to a user through a user interface.
[0019] The embodiments of the present invention further comprise a computer implemented method for an intelligent cross platform marketing resource optimization comprising:
a) trafficking a marketing campaign through a meta technology abstraction layer (MTAL) to a plurality of third party platform (TPP);
b) setting the campaign’s bid value and expenditure for each TPP;
c) tracking a plurality of key performance indicators (KPI) at a channel level as well as a system level;
d) tracing a dynamic mapping table for the KPI values and comparing each KPI value with a reference value pre-saved in the dynamic mapping table;
e) triggering a performance degradation for at least one TPP and sending the data of KPIs to the recommendation engine;
f) generating a plurality of rule based suggestions list and presenting the suggestions list to a user over a user interface of a client computing device;
g) recording an action of the user on the suggestion list and performing an optimization across the TPPs on the basis of the action by the user;
h) tracking a performance of the campaign after the recorded action and reperforming steps (c)-(g).
[0020] According to one embodiment of the present invention, the channel level KPI comprises cost per thousand impressions (CPM), cost per visit (CPV), cost per impression (CPI), cost per action (CPA) and cost per click (CPC) based on a historical data over the TPP.
[0021] According to one embodiment of the present invention, the system level KPI comprises a primary objective (also termed as a hard goal level-1), a secondary objective (also termed as a soft goal, level-2), an overall budget, impressions, reach and a campaign goal, wherein the primary objective comprises cost per thousand impressions (CPM), cost per visit (CPV), cost per impression (CPI), cost per action (CPA) and cost per click (CPC), wherein the secondary objective comprises click through rate (CTR%), conversion rate (CVR%) and a view through rate (VTR%).
[0022] According to one embodiment of the present invention, the optimization comprises a performance classification of the TPPs, a bid change, a bidding algorithm change, a cross channel expenditure budget movement, a budget increase and decrease for a campaign over a TPP, a placement change and a targeting adjustment.
[0023] According to one embodiment of the present invention, the recommendation engine and the analytical module learns from the user decision and campaign performances and provides recommendations on the value and impact on campaign performance of the hard goals and soft goals.
[0024] According to one embodiment of the present invention, the recommendation engine and the analytical module provides a guidance to a user to set realistic (deliverable) goals and also quantifies a risk involved in delivery of the campaign.
[0025] These and other aspects of the embodiments herein will be better appreciated and understood when considered in conjunction with the following description and the accompanying drawings. It should be understood, however, that the following descriptions, while indicating preferred embodiments and numerous specific details thereof, are given by way of illustration and not of limitation. Many changes and modifications may be made within the scope of the embodiments herein without departing from the spirit thereof, and the embodiments herein include all such modifications.

E) BRIEF DESCRIPTION OF DRAWINGS
[0026] The other objects, features and advantages will occur to those skilled in the art from the following description of the preferred embodiment and the accompanying drawings in which:
[0027] FIG. 1 illustrates a block diagram of a system for an intelligent cross platform marketing resource optimization, according to one embodiment of the present invention.
[0028] FIG. 1a illustrates a block diagram of the communication among a MTAL and the third party platforms (TPPs) through the marketing APIs, according to one embodiment of the present invention.
[0029] FIG. 1b illustrates a block diagram of a meta-technology abstraction layer (MTAL) to optimize a plurality of marketing parameters in the system, according to one embodiment of the present invention.
[0030] FIG. 2 illustrates a flowchart of a method for an intelligent cross platform marketing resource optimization, according to one embodiment of the present invention.
[0031] FIG. 3 illustrates a sub-routine flowchart of a method for parameter identification and updation for platform performance analysis, according to one embodiment of the present invention.
[0032] FIG. 4 illustrates a sub-routine flowchart for updating a recommendation parameter on a basis of user selections and performance of the advertisement on one or more online platforms, according to one embodiment of the present invention.
[0033] FIG. 5 illustrates a sub-routine flowchart for predicting a performance of a campaign during trafficking and in an event of an action on a recommendation, according to one embodiment of the present invention.

F) DETAILED DESCRIPTION OF DRAWINGS
[0034] In the following detailed description, a reference is made to the accompanying drawings that form a part hereof, and in which the specific embodiments that may be practiced is shown by way of illustration. The embodiments are described in sufficient detail to enable those skilled in the art to practice the embodiments and it is to be understood that the logical, mechanical and other changes may be made without departing from the scope of the embodiments. The following detailed description is therefore not to be taken in a limiting sense.
[0035] Conventional marketing optimization solutions are primarily focussed and limited to channel level key performance indicators and a campaign algorithm are optimized in absolute due to absence of monitoring and optimization agent for system level KPIs. The absence of such an optimization agent leads to wastage of huge amount investment through by an advertiser or a campaign owner in case a platform is not optimized to provide efficient returns on investment. The present investment majorly addresses this drawback in the market and provides a unique and dynamic solution to optimize a campaign launched over one or more platforms.
[0036] As shown in FIG. 1 and 1a, the system for an intelligent cross platform marketing resource optimization comprises a meta technology abstraction layer (MTAL) 101, a plurality of third party platforms (TPP) 102 and an interface module 103. The MTAL 101 is provided in a central application server 104 connected to a plurality of dedicated servers 105. The MTAL 101 comprises an analytical module 106, a trafficking module 107, a trigger module 108, a recommendation engine 109, an optimizer 110 and a predictor 111 as shown in FIG. 1b. The analytical module 106 is connected to the plurality of third party platforms 102 for collecting data pertaining to a plurality of marketing parameters which includes but not limited to cost per thousand impressions (CPM), cost per visit (CPV), cost per impression (CPI), cost per action (CPA), cost per click (CPC), click through rate (CTR%), conversion rate (CVR%) and a view through rate (VTR%). The trigger module 108 is connected to the analytical module 106 and comprises a threshold database. The threshold database comprises an optimal value of each performance data and is listed in the mapping the engine as a reference value. The recommendation engine 109 comprises a processing unit connected to the analytical module 106. The optimizer 110 is connected to the recommendation engine 109 and the plurality of third party platforms 102. The predictor 111 is connected to the analytical module, the recommendation engine 109 and the optimizer 110. The plurality of third party platforms 102 comprises a demand side platform (DSP), a data management platform (DMP) and a plurality of utility platforms. Each third party platform is situated in the dedicated server 105. The interface module 103 is an intermediatory interface between the MTAL and the plurality of third party platforms. The interface module is primarily but not limited to a marketing application programming interface (API).
[0037] As shown in FIG. 2, the monitoring and optimization of the campaign running over TPPs is achieved through a computer implemented method. The method implemented a trafficking module provided through a meta technology abstraction layer (MTAL) for trafficking a marketing campaign from a client server to a plurality of third party platform (TPP) (201). The MTAL sets the campaign’s bid value and expenditure for each TPP (202) and tracks a plurality of key performance indicators (KPI) at a channel level as well as a system level (203). The key performance indicators are dynamic in nature and are determined for a campaign on the basis of a TPP compatibility with KPIs. The MTAL traces a dynamic mapping table for the KPI values coming through user interaction with the campaign from one or TPP (204) and comparing each KPI value with a reference value pre-saved in the dynamic mapping table (205). A trigger module in the MTAL triggers a performance degradation for at least one TPP (206) and sending the data of KPIs to the recommendation engine (207). The MTAL activates a recommendation engine to generate a plurality of rule based suggestions list (208) and presents the suggestions list to a user over a user interface of a client computing device (209). An optimizer in the MTAL records an action of the user on the suggestion list (210) and performing an optimization across the TPPs on the basis of the action by the user (211). The optimizer updates the campaign parameters in the analytical module as per user’s response (212) and the optimizer restarts tracking a performance of the campaign after the recorded action and reperforming steps.
[0038] The process defined in step 212 of FIG. 2 follows a sub-routine method (as shown in FIG. 3) which comprises following steps:
a) The optimizer updates a channel level KPI and a system level KPI on identification of one or more KPIs affecting a campaign performance (301). The analytical module is prompted to analyse updates;
b) The analytical module also tracks performance of similar campaigns on the targeted TPPs to assess a TPP historical record with respect to concerned campaign nature (302);
c) In case the historical data provides a good track record of the TPP, the recommendation engine sends a set of recommendations to optimize the campaign quality through the recommendation engine (303);
d) In case the campaign quality is good and performance is better on another TPP, the recommendation engine sends a set of recommendations to redistribute the expenditure to another TPP and optimize the KPIs of the TPP with low performance (304);
e) In case the campaign and TPP both are of good quality, the recommendation engine sends a bid increase recommendation and increase the analysis period (305).
[0039] Further as shown in FIG. 4, a sub-routine method is activated on submission of user action on recommendations submitted by the recommendation engine. The sub-routine method comprises the steps of:
a) The analytical module updates the system level KPIs and the channel KPIs on the basis of the user selection and begin tracking the campaign performance on the targeted TPPs (401);
b) The analytical module saves the rejected recommendation in an event database (402);
c) The trigger module generates a trigger on sub-par performance as per the mapping the done on the basis of mapping table (403);
d) The recommendation engine requests the access to the event database and runs a diagnosis for a predicted performance of the campaign in event of accepting the previous recommendations (404);
e) In case of positive outcome of the step (d), the recommendation engine amalgamates the diagnosis graph and the generates a new set of recommendation of optimize the campaign performance on a TPP (405).
[0040] The MTAL also facilitates an activation of the predictor to predict an outcome of a campaign during trafficking. The prediction follows a sub-routine method comprising steps of:
a) Activation of the predictor automatically or on user selection during a new campaign trafficking (501);
b) The predictor module checks the event database for a match on current campaign nature with a previous campaign run on the targeted TPP (502);
c) The predictor analyses the historical performance data of the previously run campaign and the KPI values set for the current campaign (503);
d) The predictor also analyses the historical performance data of the previously run campaign on TPPs other than currently targeted TPP (504);
e) The predictor generates a graph of return on investment for the targeted TPP and other TPPs on the basis of steps (c) and (d). The user is facilitated to accept the prediction and divert the marketing resources on a single click over the graph (505);
f) The predictor is further activated on acceptance of a recommendation set by the user to show the graph of return on investment and performance of the campaign (506).
[0041] Detailed synopsis and explanation of building blocks of the business process:
[0042] Campaign trafficking, KPI setting and management:
a) Ability to traffic campaigns from the ATD platform instead of logging and setting up campaigns in individual downstream buying platforms.
b) As different channels have different parameters, field names, UI flow, targeting mechanisms, creative specifications, objective selection, algorithms, a common structure is identified among them (example- Google Ads, FB, Open Exchange DSPs) and push campaign parameters including demographic, geo, audience targeting through the marketing APIs available with each of the platforms. It will still have human intervention at particular channel levels wherever required but major portion of the campaign setup will be done in one click
c) Channel level KPIs- KPIs based on historical data or media objective will be set on individual campaigns with buying metrics like CPM, CPV, CPI, CPA/CPL/CPR, CPC etc.
d) System level KPIs: Overall budget, impressions/reach and a combination of hard goals and soft goals will be set as KPIs at the ATD system level. The underlying buying platforms will be orchestrated- bidding algorithms changed, bid values changed, targeting adjusted, budget moved across buying platforms/channels will be done to achieve the hard goal with some tolerance (user defined or system recommended) and a soft goal to cover the entire marketing funnel KPIs from branding to performance based campaigns. The system would treat the hard goal as the primary objective which won’t be compromised beyond the tolerance and will look to achieve the soft goal also without jeopardizing the primary objective in any manner. The idea behind having two goals is to ensure cost effectiveness, ROAS, objective based campaign optimization wherever needed. Soft goals are not mandatory while hard goals are. All metrices that can be set as hard goals can also be set as soft goals and vice-e-versa. There will be campaign pacing and budget management by ensuring the overall budget is in sync with the underlying channel budgets and at no point exceeds the overall budget assigned for the campaign. Pacing is a measure of delivery of the campaign by measuring the projected spends with actual spends or against the primary delivery objective. There will also be provision to set time frequency at which the goals are to be met. Example- 1000 leads/conversions every week, 50,000 Video Ad Views in a day.
[0043] Rules/Triggers (System-level, Channel level) and actions: There are two ways triggers will be set and implemented. Firstly- semi-automated manner, where the user would be able to put certain KPI values as triggers and associate actions with them. Example: Increasing budget for a particular channel by a factor of 1.5 in case the CTR% is above 0.8% for that channel. Other use cases will be provided in the addendum. Using decision trees these triggers will fire at channel level and only the firing is automated. Over a period of time the meta system will learn the triggers put into the channels, measure performance changes and come up with trigger recommendation at channel levels. Over a period of time the user can disable manual override and choose for a completely automated mode to run campaigns where triggers get implemented and the user is just notified of the changes implemented. The system works either as a completely automated self-balancing, self-optimizing, self-learning system or using an ensemble of human inputs and recommendation systems to achieve campaign objectives.
[0044] Campaign optimization (by constantly taking feedback from the underlying channels):
a) Classification of campaigns in to – High, Mid and Low performing or potentially High, Mid and Low performing ones using classification models in machine learning
b) Bid changes: Change bid values like CPM, CPC, Target CPA/CPR/CPL wherever possible. Example- Possible in Google Ads, Dv360, Verizon, Media Math, Adobe, The Trade Desk etc. Not possible in certain mediums like Facebook. Changes would mean increasing and decreasing the bid by comparing with historical data and predict current values using linear regression techniques by reducing mean errors and arriving at value of estimators by constant learning by various models. It will perform predictive analysis and take decisions based on the likely impact these changes will have on performance and delivery of these campaigns. A copy of the changes is sent to the database to keep a track of positive/negative/neutral impact of these changes on the campaign. For open-exchange DSPs the system changes senses and changes the bid values rather frequently and also develops custom bidding algorithms for optimized campaign spending.
c) Bidding algorithm changes: Most biddable media platforms have inherent algorithms that are deployed for buying media based on client/campaign objective. The campaigns initially go into learning phase and then start optimizing based on the learnings. Any change in bidding algorithms are only recommended after 7-10days and this translates to constant monitoring of the campaigns, human resource bandwidth allocation. The system will have the ability to change the bidding algorithms either by recommending an algorithm change and then based on user input implementing it or choose and algorithm by itself and implement it, notifying the user of a change that has been made and keeping track of the changes in an automated manner, when substantial learning has been obtained at the meta system level (6-12 weeks)
d) Cross channel budget movement, budget increase/decrease: Based on performing channels/buying platforms, the meta layer will first recommend budget changes which will be accepted or denied by the users and over a period of time after sufficient learning system should be able to make those changes on the fly even in case hardcoded triggers are not put in place for the channel or campaign. This will ensure budgets are spent platform agnostically with sole focus on only meeting client objectives and thereby moving budgets to channels which are either performing well or system decides are likely to perform well
e) Site/placement level changes: Identify which supply sources across sites, platforms, devices (Desktop, Mobile, Mac, etc), channels (Web, Mobile Web, Mobile APP etc), Operating systems (iOS, Android, etc)
f) Targeting adjustment: Geo targeting, audience demography targeting
[0045] Planning and buying forecasting: By keeping a track of all campaign spends/learnings, seasonality, sector the system would be able to provide buying and planning forecasting of supply to have pre-campaign understanding of budget estimates which currently either happens in silos or through silos and in a non-integrated manner
[0046] Data Management Platform: At any point of time there will either be a partnership with a global vendor or a proprietary platform for collection, enrichment and activation of 1st party campaign data through online and offline channels for cross channel activation, retargeting campaigns, consumer understanding, audience adjustment, personalization through the buying platforms integrated either through APIs or S2S integration. The ability to infuse 3rd party 7 2nd party audience to cross-pollinate with existing 1st party data is also possible.
[0047] Machine learning models: Models will be developed based on historical data and ongoing data to achieve four key objectives- (a) Learn channel level triggers, system level KPIs and recommendation of the same by self-learning (b) Learn which versions of the campaign changes worked better than other and ability to classify potentially performing and non-performing campaigns (c) Take human approval/disapproval of the system level and channel level triggers recommendation as feedback to learn and come up with better optimization suggestions (d) Help supply forecasting and planning
[0048] 360-degree reporting: Data pulled across channels/buying platforms in an hourly, daily, weekly, monthly, quarterly, yearly fashion to give single view of the audience by collating data from all channels
[0049] Data base schema and instances: Three data base instances are to be maintained with distinct objective- (a) Store ongoing campaign data and ability to fetch data on a real time basis for campaign analysis (b) Historic data of all campaign trafficking details (including creatives), campaign data, channel level triggers, system level triggers for serving as a backup and restore mechanism. (c) Execution of various learning models using neural networks, recommendation systems, linear regression and ensemble wherever required.
[0050] Marketing APIs: Open source APIs available used within the available thresholds to fetch campaign data from all underlying channels. These include but are not limited to Impressions, CPM (Cost per mile), CTR %(Click Through rate), Budget spent (Cost), Leads/Conversions/Results, CPA/CPR/CPL (Cost per acquisition, Cost per results, Cost per lead), Views, True Views, Thru plays, 3 sec views, 5 sec views, VTR%( View Through Rate), VCR% (Video Completion Rate), Offsite conversions, onsite conversions, Unique user, reach etc. User of the platform are able to drill down to Campaign level, ad group level, creative level, targeting (age gender, geo) level and affinity audience level.
[0051] The present invention finds application in other business processes also such as:
a) Advertising technology layer to facilitate demand-supply chain automated campaign management and optimization based on quantitative analysis of objectives using semi-automated to fully autonomous meta data technology layer backed by machine learning models
b) Portfolio management (B2C/B2B finance): Single technology layer to manage, grow and sell funds with ability to set clear objectives like stable asset management, monthly/quarterly/yearly fixed returns or variable returns with tolerance but with secondary objective like maintaining high equity ratio, high debt ratio, maintain returns at a specified percentage. This happens in converse true and by setting a certain tolerance at the hard goal or primary objective. AUM can include- stocks (intraday/CNC/Commodities, Futures and options etc.), fixed deposits, savings account, digital gold, bonds, cryptocurrency etc.
c) Real Estate management
d) Logistics management
e) Travel & Hospitality management
f) Healthcare management
g) Food aggregators
h) Cab aggregators
i) Utilities aggregators
j) Agriculture marketplace
[0052] The channel level KPI comprises cost per thousand impressions (CPM), cost per visit (CPV), cost per impression (CPI), cost per action (CPA) and cost per click (CPC) based on a historical data over the TPP.
[0053] According to one embodiment of the present invention, the system level KPI comprises a primary objective, a secondary objective, an overall budget, impressions, reach and a campaign goal, wherein the primary objective comprises cost per thousand impressions (CPM), cost per visit (CPV), cost per impression (CPI), cost per acquisition (CPA) and cost per click (CPC), wherein the secondary objective comprises click through rate (CTR%), Video Completion Rate (VCR%), number of leads (lead flow in a designated time period) and a view through rate (VTR%).
[0054] For example - Performance - Level 1 – CPM,CPA/CPL, CPC, CTR%; Level 2- Maintaining lead flow (range/threshold/absolute) number with Time frequency (Daily/weekly/monthly).
[0055] Branding- Level 1- CPM, CPV; Level 2- VCR% (Video Completion Rate), VTR% (View Through Rate), Views, CPC, CTR%.
[0056] The performance and branding levels form primary and secondary objective and both levels can be put in place with a “Boolean &&” operator to satisfy both levels at a time with a certain tolerance of the primary KPI, say 10%. Example: CPM set as Primary KPI and CTR set as secondary KPI. The system will have to meet CPM KPI with a 10% tolerance to try and meet the secondary KPI of CTR%. Level 1 is always compulsory, and Level 1 and Level 2 are switchable.
[0057] It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the spirit and scope of the claims.