Search

KR-20260062869-A - SERVER, METHOD AND COMPUTER PROGRAM FOR PREDICTING THE EFFECTIVENESS OF ADVERTISING

KR20260062869AKR 20260062869 AKR20260062869 AKR 20260062869AKR-20260062869-A

Abstract

A server providing a service for predicting the efficiency of an advertisement comprises: a receiving unit that receives advertising data representing the performance of an advertisement from at least one advertising channel; a learning unit that preprocesses the advertising data and trains a plurality of deep learning models based on the preprocessed advertising data; a prediction unit that predicts and provides a result value for an advertising performance indicator, including any one of Click-Through Rate (CTR), Conversion Rate (CVR), Return on Ad Spend (ROAS), and Cost Per Action (CPA), for each advertising medium by performing mixed inference from the plurality of deep learning models; and a providing unit that generates and provides a predicted result value for the advertising performance indicator as visualized data by undergoing post-processing on the result value, wherein the plurality of deep learning models include any one of a Convolutional Neural Network (CNN), a Recurrent Neural Network (RNN), and XGBoost (eXtreme Gradient Boosting).

Inventors

  • 이병갑
  • 모선영
  • 김도수

Assignees

  • 애디플 주식회사

Dates

Publication Date
20260507
Application Date
20251027
Priority Date
20241025

Claims (11)

  1. In a server that provides a service for predicting the efficiency of advertisements, A receiver that receives advertising data indicating the performance of an advertisement from at least one advertising channel; A learning unit that preprocesses the above-mentioned advertisement data and trains a plurality of deep learning models based on the preprocessed advertisement data; A prediction unit that predicts and provides a result value for an advertising performance indicator, including any one of Click-Through Rate (CTR), Conversion Rate (CVR), Return on Ad Spend (ROAS), and Cost Per Action (CPA), for each advertising medium by performing mixed inference from the plurality of deep learning models; and A providing unit that generates and provides visualized data of predicted result values for the advertising performance indicators after post-processing the above result values. Includes, An advertising efficiency prediction server in which the above plurality of deep learning models include any one of a Convolutional Neural Network (CNN), a Recurrent Neural Network (RNN), and XGBoost (eXtreme Gradient Boosting).
  2. In Article 1, The above learning unit is, Generate each prediction value for the above convolutional neural network, recurrent neural network, and XGBoost, and metamodel the prediction values, An advertising efficiency prediction server based on a MultiLayer Perceptron (MLP) as a metamodel.
  3. In Article 2, The above learning unit is, The above convolutional neural network is input with an advertisement image and video to output a result value representing the advertisement image and video, and Time series data regarding advertising performance indicators for a preset period is input into the above recurrent neural network to output predicted values for click-through rates and conversion rates for the preset period, and An advertising efficiency prediction server that inputs tabular data including any one of an ad channel, region, time, bid price (CPC: Cost per Click), budget, and statistics into the above XGBoost to output a prediction for an advertising performance indicator.
  4. In Paragraph 3, The above learning unit is, An advertising efficiency prediction server that inputs result values representing the advertising image and video, predicted values for the click-through rate and transmission rate during the preset period, and predicted values for the advertising performance indicator into the metamodel to provide predicted result values for the final advertising performance indicator.
  5. In Article 1, An advertising efficiency prediction server in which the above-mentioned visualized data includes any one of the following: predicted result values for the above-mentioned advertising performance indicators, rankings by advertising channel and creative, information proposing an advertising budget plan, and advertising forecasts for a preset period.
  6. In a method for providing a service that predicts the efficiency of advertising, A step of receiving advertising data indicating the performance of an advertisement from at least one advertising channel; A step of preprocessing the above-mentioned advertising data and training a plurality of deep learning models based on the preprocessed advertising data; A step of predicting and providing a result value for an advertising performance indicator, including any one of Click-Through Rate (CTR), Conversion Rate (CVR), Return on Ad Spend (ROAS), and Cost Per Action (CPA), for each advertising medium by performing blended inference from the plurality of deep learning models; and A step of generating and providing visualized data of predicted result values for the advertising performance indicators through post-processing of the above result values. Includes, A method for predicting advertising efficiency, wherein the plurality of deep learning models includes any one of a Convolutional Neural Network (CNN), a Recurrent Neural Network (RNN), and XGBoost (eXtreme Gradient Boosting).
  7. In Article 6, The step of training the above plurality of deep learning models is, A step of generating each prediction value for the above convolutional neural network, recurrent neural network, and XGBoost; and Step of metamodeling the above predicted values Includes, An advertising efficiency prediction method based on a MultiLayer Perceptron (MLP) as a metamodel.
  8. In Article 7, The step of training the above plurality of deep learning models is, A step of inputting an advertisement image and video into the above convolutional neural network and outputting a result value representing the advertisement image and video; A step of inputting time series data regarding advertising performance indicators for a preset period into the above recurrent neural network to output predicted values for click-through rates and conversion rates for a preset period; and A step of inputting tabular data including any one of ad channel, region, time, bid price (CPC: Cost per Click), budget, and statistics into the above XGBoost to output a prediction for ad performance indicators. An advertising efficiency prediction method that includes
  9. In Article 8, The step of training the above plurality of deep learning models is, A step of providing a predicted result value for the final advertising performance indicator by inputting the result value representing the advertising image and video, the predicted value for the click-through rate and transmission rate during the preset period, and the predicted value for the advertising performance indicator into the metamodel. An advertising efficiency prediction method that includes
  10. In Article 6, A method for predicting advertising efficiency, wherein the above-mentioned visualized data includes any one of the following: predicted result values for the above-mentioned advertising performance indicators, rankings by advertising channel and creative, information proposing an advertising budget plan, and advertising forecasts for a preset period.
  11. In a computer program stored on a computer-readable recording medium comprising a sequence of instructions that provide a service for predicting the efficiency of advertisements, When the above computer program is executed by a computing device, Receiving advertising data indicating the performance of an advertisement from at least one advertising channel, and The above advertising data is preprocessed, and a plurality of deep learning models are trained based on the preprocessed advertising data, and By performing blended inference from the aforementioned multiple deep learning models, a result value for an advertising performance indicator including any one of Click-Through Rate (CTR), Conversion Rate (CVR), Return on Ad Spend (ROAS), and Cost Per Action (CPA) for each advertising medium is predicted and provided. The predicted result value for the above advertising performance indicator is generated as visualized data and provided after undergoing post-processing of the above result value, A computer program stored on a computer-readable recording medium, wherein the plurality of deep learning models comprises a sequence of instructions including any one of a Convolutional Neural Network (CNN), a Recurrent Neural Network (RNN), and XGBoost (eXtreme Gradient Boosting).

Description

Server, Method and Computer Program for Predicting the Effectiveness of Advertising The present invention relates to a server, a method, and a computer program for predicting the efficiency of advertising. Advertising performance prediction technology is the process of forecasting future advertising results through data analysis. To this end, various Key Performance Indicators (KPIs) are analyzed, and if performance is poor, issues such as product detail pages, keywords, and bidding strategies are diagnosed. Recently, solutions utilizing AI technology to assist in optimal budget allocation and campaign strategy formulation have also emerged. However, conventional advertising performance prediction technologies have limitations in processing statistically non-linear patterns and large-scale data, and since automation is limited to a single advertising channel, they suffer from the disadvantage of significant operational complexity and resource waste when managing multiple advertising channels. Figure 1 is a configuration diagram of an advertising efficiency prediction server. Figure 2 is an exemplary diagram of multiple deep learning models. Figure 3A is an exemplary diagram of visualized data. Figure 3B is an exemplary diagram of visualized data. Figure 4 is a flowchart of the advertising efficiency prediction method. Embodiments of the present invention are described below with reference to the attached drawings so that those skilled in the art can easily implement the invention. However, the present invention may be embodied in various different forms and is not limited to the embodiments described herein. Furthermore, in order to clearly explain the present invention in the drawings, parts unrelated to the explanation have been omitted, and similar parts throughout the specification are denoted by similar reference numerals. Throughout the specification, when a part is described as being "connected" to another part, this includes not only cases where they are "directly connected" but also cases where they are "electrically connected" with other elements interposed between them. Furthermore, when a part is described as "including" a component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components, and it should be understood that this does not preclude the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof. In this specification, the term "part" includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Additionally, one unit may be realized using two or more hardware, and two or more units may be realized by one hardware. Some of the operations or functions described in this specification as being performed by a terminal or device may instead be performed by a server connected to said terminal or device. Likewise, some of the operations or functions described as being performed by a server may also be performed by a terminal or device connected to said server. An embodiment of the present invention will be described in detail below with reference to the attached drawings. FIG. 1 is a configuration diagram of an advertising efficiency prediction server. Referring to FIG. 1, the advertising efficiency prediction server (100) may include a receiving unit (110), a learning unit (120), a prediction unit (130), and a providing unit (140). However, the above components (110 to 140) are merely illustrative examples of components that can be controlled by the advertising efficiency prediction server (100). Each component of the advertising efficiency prediction server (100) of FIG. 1 is generally connected via a network. For example, as shown in FIG. 1, the receiving unit (110), the learning unit (120), the prediction unit (130), and the providing unit (140) can be connected simultaneously or at intervals. A network refers to a connection structure capable of exchanging information among respective nodes, such as terminals and servers, and includes local area networks (LAN), wide area networks (WAN), the internet (WWW: World Wide Web), wired and wireless data communication networks, telephone networks, wired and wireless television communication networks, etc. Examples of wireless data communication networks include, but are not limited to, 3G, 4G, 5G, 3GPP (3rd Generation Partnership Project), LTE (Long Term Evolution), WIMAX (World Interoperability for Microwave Access), Wi-Fi, Bluetooth communication, infrared communication, ultrasonic communication, visible light communication (VLC), and LiFi. The advertising efficiency prediction server (100) can predict advertising performance for each advertising channel based on advertising performance data collected for each advertising channel. For example, the advertising prediction server (100) can collect advertising banners, thumbnail images, and videos used in each advertising chann