Return on Advertising Spend Prediction with Task Decomposition-Based LSTM Model
Return on advertising spend (ROAS) refers to the ratio of revenue generated by advertising projects to its expense. It is used to assess the effectiveness of advertising marketing. Several simulation-based controlled experiments, such as geo experiments, have been proposed recently. This refers to c...
Main Authors: | , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-05-01
|
Series: | Mathematics |
Subjects: | |
Online Access: | https://www.mdpi.com/2227-7390/10/10/1637 |
_version_ | 1797498160940056576 |
---|---|
author | Hyeonseok Moon Taemin Lee Jaehyung Seo Chanjun Park Sugyeong Eo Imatitikua D. Aiyanyo Jeongbae Park Aram So Kyoungwha Ok Kinam Park |
author_facet | Hyeonseok Moon Taemin Lee Jaehyung Seo Chanjun Park Sugyeong Eo Imatitikua D. Aiyanyo Jeongbae Park Aram So Kyoungwha Ok Kinam Park |
author_sort | Hyeonseok Moon |
collection | DOAJ |
description | Return on advertising spend (ROAS) refers to the ratio of revenue generated by advertising projects to its expense. It is used to assess the effectiveness of advertising marketing. Several simulation-based controlled experiments, such as geo experiments, have been proposed recently. This refers to calculating ROAS by dividing a geographic region into a control group and a treatment group and comparing the ROAS generated in each group. However, the data collected through these experiments can only be used to analyze previously constructed data, making it difficult to use in an inductive process that predicts future profits or costs. Furthermore, to obtain ROAS for each advertising group, data must be collected under a new experimental setting each time, suggesting that there is a limitation in using previously collected data. Considering these, we present a method for predicting ROAS that does not require controlled experiments in data acquisition and validates its effectiveness through comparative experiments. Specifically, we propose a task deposition method that divides the end-to-end prediction task into the two-stage process: occurrence prediction and occurred ROAS regression. Through comparative experiments, we reveal that these approaches can effectively deal with the advertising data, in which the label is mainly set to zero-label. |
first_indexed | 2024-03-10T03:29:29Z |
format | Article |
id | doaj.art-fc276928de30491b91c6399237e35312 |
institution | Directory Open Access Journal |
issn | 2227-7390 |
language | English |
last_indexed | 2024-03-10T03:29:29Z |
publishDate | 2022-05-01 |
publisher | MDPI AG |
record_format | Article |
series | Mathematics |
spelling | doaj.art-fc276928de30491b91c6399237e353122023-11-23T12:00:11ZengMDPI AGMathematics2227-73902022-05-011010163710.3390/math10101637Return on Advertising Spend Prediction with Task Decomposition-Based LSTM ModelHyeonseok Moon0Taemin Lee1Jaehyung Seo2Chanjun Park3Sugyeong Eo4Imatitikua D. Aiyanyo5Jeongbae Park6Aram So7Kyoungwha Ok8Kinam Park9Department of Computer Science and Engineering, Korea University, Seoul 02841, KoreaHuman Inspired Artificial Intelligence Research (HIAI), Korea University, Seoul 02841, KoreaDepartment of Computer Science and Engineering, Korea University, Seoul 02841, KoreaDepartment of Computer Science and Engineering, Korea University, Seoul 02841, KoreaDepartment of Computer Science and Engineering, Korea University, Seoul 02841, KoreaHuman Inspired Artificial Intelligence Research (HIAI), Korea University, Seoul 02841, KoreaHuman Inspired Artificial Intelligence Research (HIAI), Korea University, Seoul 02841, KoreaHuman Inspired Artificial Intelligence Research (HIAI), Korea University, Seoul 02841, KoreaAI Data Business Operation, Bizspring, Seoul 04788, KoreaHuman Inspired Artificial Intelligence Research (HIAI), Korea University, Seoul 02841, KoreaReturn on advertising spend (ROAS) refers to the ratio of revenue generated by advertising projects to its expense. It is used to assess the effectiveness of advertising marketing. Several simulation-based controlled experiments, such as geo experiments, have been proposed recently. This refers to calculating ROAS by dividing a geographic region into a control group and a treatment group and comparing the ROAS generated in each group. However, the data collected through these experiments can only be used to analyze previously constructed data, making it difficult to use in an inductive process that predicts future profits or costs. Furthermore, to obtain ROAS for each advertising group, data must be collected under a new experimental setting each time, suggesting that there is a limitation in using previously collected data. Considering these, we present a method for predicting ROAS that does not require controlled experiments in data acquisition and validates its effectiveness through comparative experiments. Specifically, we propose a task deposition method that divides the end-to-end prediction task into the two-stage process: occurrence prediction and occurred ROAS regression. Through comparative experiments, we reveal that these approaches can effectively deal with the advertising data, in which the label is mainly set to zero-label.https://www.mdpi.com/2227-7390/10/10/1637deep learningartificial intelligencereturn on advertising spendtask decompositionprediction model |
spellingShingle | Hyeonseok Moon Taemin Lee Jaehyung Seo Chanjun Park Sugyeong Eo Imatitikua D. Aiyanyo Jeongbae Park Aram So Kyoungwha Ok Kinam Park Return on Advertising Spend Prediction with Task Decomposition-Based LSTM Model Mathematics deep learning artificial intelligence return on advertising spend task decomposition prediction model |
title | Return on Advertising Spend Prediction with Task Decomposition-Based LSTM Model |
title_full | Return on Advertising Spend Prediction with Task Decomposition-Based LSTM Model |
title_fullStr | Return on Advertising Spend Prediction with Task Decomposition-Based LSTM Model |
title_full_unstemmed | Return on Advertising Spend Prediction with Task Decomposition-Based LSTM Model |
title_short | Return on Advertising Spend Prediction with Task Decomposition-Based LSTM Model |
title_sort | return on advertising spend prediction with task decomposition based lstm model |
topic | deep learning artificial intelligence return on advertising spend task decomposition prediction model |
url | https://www.mdpi.com/2227-7390/10/10/1637 |
work_keys_str_mv | AT hyeonseokmoon returnonadvertisingspendpredictionwithtaskdecompositionbasedlstmmodel AT taeminlee returnonadvertisingspendpredictionwithtaskdecompositionbasedlstmmodel AT jaehyungseo returnonadvertisingspendpredictionwithtaskdecompositionbasedlstmmodel AT chanjunpark returnonadvertisingspendpredictionwithtaskdecompositionbasedlstmmodel AT sugyeongeo returnonadvertisingspendpredictionwithtaskdecompositionbasedlstmmodel AT imatitikuadaiyanyo returnonadvertisingspendpredictionwithtaskdecompositionbasedlstmmodel AT jeongbaepark returnonadvertisingspendpredictionwithtaskdecompositionbasedlstmmodel AT aramso returnonadvertisingspendpredictionwithtaskdecompositionbasedlstmmodel AT kyoungwhaok returnonadvertisingspendpredictionwithtaskdecompositionbasedlstmmodel AT kinampark returnonadvertisingspendpredictionwithtaskdecompositionbasedlstmmodel |