Programmatic Marketing via Reinforcement Learning

Journal Title: Journal of Business Management & Economics - Year 2017, Vol 5, Issue 11

Abstract

This new algorithm which incorporates look-ahead search inside the training loop resulting in rapid improvement and precise and stable learning. By using this new search methods towards programmatic marketing, we massively improve the return of investment on Google Adwords auction by 4.6% in 1 day. We apply simple, gradient-based updates to train the next policy and value network. This appears to be much more stable than incremental, gradient-based policy improvements such as policy gradient or Q-learning that can potentially forget previous improvements.

Authors and Affiliations

Mengmeng Chen, Luis Rabelo

Keywords

Related Articles

Proposal For Research In Novation Capacity As A Factorin The Competitiveness Of Software Industry Of Jalisco

The aimof this workis to proposea research to determine anindex to measureinnovation capacityofenterprises in thesoftware industry ofJalisco, based on a survey ofthecompanies in theSoftwareCenterof the State,as well as e...

Housing Price Leads Rent in Hong Kong? -- A Puzzle of Rent-Price Theory

This study analyzes the lead-lag relationships between housing price growths, rent growths and the expected housing rent changes. Theories, including the Di Pasquale-Wheaton (DW) Model, assumes housing price as a discoun...

Firm and Borrower Characteristics for Performance of Micro and Small Enterprises (MSEs): Evidence from Micro Finance Institutions (MFIs) in Uganda

Most SMEs lack collateral security which is required by commercial banks to access credit and as a result, they end up borrowing from MFIs. The study aimed to identify to what extent firm and borrower characteristics inf...

Recommendations for Enhancing Student Satisfaction with Service Quality of Dormitory at Lac Hong University

According to statistics by the Ministry of education and training announced the end of 2016, there are about 400 universities, colleges, with about three million students are studying at the universities, colleges. Of th...

Taxonomy of Public Clouds for the Next Generation of ICT Development

Since the information and communications technology (ICT) development was a policy of national competitive advantages to support the 21st-century development of Asia-Pacific countries decades ago, computing technology ha...

Download PDF file
  • EP ID EP321302
  • DOI 10.15520/jbme.2017.vol5.iss11.269.pp01-04
  • Views 57
  • Downloads 0

How To Cite

Mengmeng Chen, Luis Rabelo (2017). Programmatic Marketing via Reinforcement Learning. Journal of Business Management & Economics, 5(11), 1-4. https://europub.co.uk/articles/-A-321302