The Reserve Price Optimization for Publishers on Real-Time Bidding on-Line Marketplaces with Time-Series Forecasting
Today's Internet marketing ecosystems are very complex, with many competing players, transactions concluded within milliseconds, and hundreds of different parameters to be analyzed in the decision-making process. In addition, both sellers and buyers operate under uncertainty, without full infor...
Main Author: | |
---|---|
Format: | Article |
Language: | English |
Published: |
Sciendo
2020-11-01
|
Series: | Foundations of Management |
Subjects: | |
Online Access: | https://doi.org/10.2478/fman-2020-0013 |
id |
doaj-9bd6e73ad47643e6b65963ba81cb34eb |
---|---|
record_format |
Article |
spelling |
doaj-9bd6e73ad47643e6b65963ba81cb34eb2021-09-05T21:00:59ZengSciendoFoundations of Management2300-56612020-11-0112116718010.2478/fman-2020-0013fman-2020-0013The Reserve Price Optimization for Publishers on Real-Time Bidding on-Line Marketplaces with Time-Series ForecastingWodecki Andrzej0Warsaw University of Technology, Faculty of Management, Warsaw, POLANDToday's Internet marketing ecosystems are very complex, with many competing players, transactions concluded within milliseconds, and hundreds of different parameters to be analyzed in the decision-making process. In addition, both sellers and buyers operate under uncertainty, without full information about auction results, purchasing preferences, and strategies of their competitors or suppliers. As a result, most market participants strive to optimize their trading strategies using advanced machine learning algorithms. In this publication, we propose a new approach to determining reserve-price strategies for publishers, focusing not only on the profits from individual ad impressions, but also on maximum coverage of advertising space. This strategy combines the heuristics developed by experienced RTB consultants with machine learning forecasting algorithms like ARIMA, SARIMA, Exponential Smoothing, and Facebook Prophet. The paper analyses the effectiveness of these algorithms, recommends the best one, and presents its implementation in real environment. As such, its results may form a basis for a competitive advantage for publishers on very demanding online advertising markets.https://doi.org/10.2478/fman-2020-0013online marketingreal-time biddingreserve price optimizationmachine learningforecastingc53c57m37m39 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Wodecki Andrzej |
spellingShingle |
Wodecki Andrzej The Reserve Price Optimization for Publishers on Real-Time Bidding on-Line Marketplaces with Time-Series Forecasting Foundations of Management online marketing real-time bidding reserve price optimization machine learning forecasting c53 c57 m37 m39 |
author_facet |
Wodecki Andrzej |
author_sort |
Wodecki Andrzej |
title |
The Reserve Price Optimization for Publishers on Real-Time Bidding on-Line Marketplaces with Time-Series Forecasting |
title_short |
The Reserve Price Optimization for Publishers on Real-Time Bidding on-Line Marketplaces with Time-Series Forecasting |
title_full |
The Reserve Price Optimization for Publishers on Real-Time Bidding on-Line Marketplaces with Time-Series Forecasting |
title_fullStr |
The Reserve Price Optimization for Publishers on Real-Time Bidding on-Line Marketplaces with Time-Series Forecasting |
title_full_unstemmed |
The Reserve Price Optimization for Publishers on Real-Time Bidding on-Line Marketplaces with Time-Series Forecasting |
title_sort |
reserve price optimization for publishers on real-time bidding on-line marketplaces with time-series forecasting |
publisher |
Sciendo |
series |
Foundations of Management |
issn |
2300-5661 |
publishDate |
2020-11-01 |
description |
Today's Internet marketing ecosystems are very complex, with many competing players, transactions concluded within milliseconds, and hundreds of different parameters to be analyzed in the decision-making process. In addition, both sellers and buyers operate under uncertainty, without full information about auction results, purchasing preferences, and strategies of their competitors or suppliers. As a result, most market participants strive to optimize their trading strategies using advanced machine learning algorithms. In this publication, we propose a new approach to determining reserve-price strategies for publishers, focusing not only on the profits from individual ad impressions, but also on maximum coverage of advertising space. This strategy combines the heuristics developed by experienced RTB consultants with machine learning forecasting algorithms like ARIMA, SARIMA, Exponential Smoothing, and Facebook Prophet. The paper analyses the effectiveness of these algorithms, recommends the best one, and presents its implementation in real environment. As such, its results may form a basis for a competitive advantage for publishers on very demanding online advertising markets. |
topic |
online marketing real-time bidding reserve price optimization machine learning forecasting c53 c57 m37 m39 |
url |
https://doi.org/10.2478/fman-2020-0013 |
work_keys_str_mv |
AT wodeckiandrzej thereservepriceoptimizationforpublishersonrealtimebiddingonlinemarketplaceswithtimeseriesforecasting AT wodeckiandrzej reservepriceoptimizationforpublishersonrealtimebiddingonlinemarketplaceswithtimeseriesforecasting |
_version_ |
1717781858426552320 |