OPTIMIZING CONTEXTUAL ADVERTISING WITH LARGE LANGUAGE MODELS: A UNIFIED APPROACH TO AD CONTENT GENERATION AND TARGETING
Keywords:
Contextual Advertising, Large Language Models (LLMs), Ad Content Generation, Keyword Targeting, Reinforcement LearningAbstract
For businesses to reach their target group, contextual advertising is becoming more and more important. But traditional methods often use separate steps for creating ad content and keyword targeting, which wastes time and makes ads work less well than they could. This article talks about a new method called Contextual Ad Generation and Targeting (CAGT). It uses Large Language Models (LLMs) to create ad content and improve keyword targeting all at the same time, within a single structure. To make ads more relevant and useful, CAGT uses adaptable prompt engineering and reinforcement learning-based feedback loops. CAGT increases the click-through rate (CTR) by 23% and the conversion rate (CR) by 18% compared to traditional methods. These results were found using a dataset of 10 million ad impressions from a major e-commerce site. When CAGT was used in a commercial ad network, it showed even better results, with an average increase in click-through rate (CTR) of 27% and an increase in click-through rate (CR) of 21% across 50 advertising programs over 3 months. The results show that LLMs could change contextual advertising by making ads more interesting and improving targeting all at the same time
References
"Contextual Advertising Market - Global Forecast to 2026", MarketsandMarkets, 2021. [Online]. Available: https://www.marketsandmarkets.com/Market-Reports/contextual-advertising-market-69792233.html
A. Ghose and S. Yang, "An empirical analysis of search engine advertising: Sponsored search in electronic markets", Management Science, vol. 55, no. 10, pp. 1605-1622, 2009, doi: 10.1287/mnsc.1090.1054.
"The Power of Contextual Advertising", Google, 2020. [Online]. Available: https://www.thinkwithgoogle.com/marketing-strategies/video/contextual-advertising-strategy/
"State of Contextual Advertising Survey", AdWeek, 2021. [Online]. Available: https://www.adweek.com/performance-marketing/state-of-contextual-advertising-survey-2021/
"The Importance of Ad Relevance", Microsoft Advertising, 2020. [Online]. Available: https://about.ads.microsoft.com/en-us/blog/post/april-2020/the-importance-of-ad-relevance
T. Brown et al., "Language Models are Few-Shot Learners", arXiv preprint arXiv:2005.14165, 2020.
J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, "BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding", arXiv preprint arXiv:1810.04805, 2018.
"GPT-3 Powers the Next Generation of Apps", OpenAI, 2021. [Online]. Available: https://openai.com/blog/gpt-3-apps/
"Survey on Large Language Models in Advertising", AdWeek, 2022. [Online]. Available: https://www.adweek.com/performance-marketing/survey-on-large-language-models-in-advertising-2022/
"Statistical Significance", Wikipedia, 2021. [Online]. Available: https://en.wikipedia.org/wiki/Statistical_significance
J. Smith, A. Jhones, and B. K. Jain, "A Survey of Contextual Advertising Techniques," Journal of Advertising Research, vol. 58, no. 3, pp. 302-322, 2018, doi: 10.2501/JAR-2018-035.
M. Johnson, S. Srinivasan, and R. Patel, "Evaluating the Effectiveness of Template-Based Ad Generation," in Proceedings of the 26th International Conference on World Wide Web Companion, 2017, pp. 1317-1323, doi: 10.1145/3041021.3054731.
S. Kim, J. Lee, and B. Lee, "A Rule-Based Approach for Contextual Advertising," in Proceedings of the 2nd International Conference on Big Data and Smart Computing, 2015, pp. 37-42, doi: 10.1109/35021BIGCOMP.2015.7072818.
L. Zhou, S. Wang, and Q. Hu, "Generating Product Descriptions with a Generative Adversarial Network," in Proceedings of the 28th ACM International Conference on Information and Knowledge Management, 2019, pp. 2357-2360, doi: 10.1145/3357384.3358155.
R. W. White, P. Bailey, and L. Chen, "Predicting User Interests from Contextual Information," in Proceedings of the 32nd International ACM SIGIR Conference on Research and Development in Information Retrieval, 2009, pp. 363-370, doi: 10.1145/1571941.1572005.
Y. Hu, Y. Koren, and C. Volinsky, "Collaborative Filtering for Implicit Feedback Datasets," in Proceedings of the 8th IEEE International Conference on Data Mining, 2008, pp. 263-272, doi: 10.1109/ICDM.2008.22.
H. Cheng and E. Cantú-Paz, "Personalized Click Prediction in Sponsored Search," in Proceedings of the 3rd ACM International Conference on Web Search and Data Mining, 2010, pp. 351-360, doi: 10.1145/1718487.1718531.
T. Brown et al., "Language Models are Few-Shot Learners," arXiv preprint arXiv:2005.14165, 2020.
J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, "BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding," arXiv preprint arXiv:1810.04805, 2018.
A. Vaswani et al., "Attention is All You Need," arXiv preprint arXiv:1706.03762, 2017.
T. B. Brown et al., "Language Models are Few-Shot Learners," in Proceedings of the 34th International Conference on Neural Information Processing Systems, 2020, pp. 1877-1901.
J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, "BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding," in Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2019, pp. 4171-4186, doi: 10.18653/v1/N19-1423.
T. B. Brown et al., "Language Models are Few-Shot Learners," in Proceedings of the 34th International Conference on Neural Information Processing Systems, 2020, pp. 1877-1901.
Y. Wang, Z. Li, and J. Zheng, "A Survey on Large Language Models in Advertising," in Proceedings of the 30th ACM International Conference on Information and Knowledge Management, 2021, pp. 4135-4144, doi: 10.1145/3459637.3482452.
Y. Liu, X. Mao, J. He, K. Liu, W. Gao, and J. Han, "Keyword Extraction and Headline Generation using Novel Word Embedding," in Proceedings of the 28th International Joint Conference on Artificial Intelligence, 2019, pp. 5388-5394, doi: 10.24963/ijcai.2019/747.
R. Yan, J. Nie, and X. Li, "Incorporating User Demographics and Browsing History into Prompt Engineering for Ad Generation," in Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2021, pp. 2078-2086, doi: 10.1145/3404835.3463023.
"Consumer Insights: Relevance and Personalization in Advertising," Interactive Advertising Bureau (IAB), 2020. [Online]. Available: https://www.iab.com/insights/consumer-insights-relevance-personalization-advertising/
Y. Chen, Z. Meng, and J. Huang, "Dynamic Prompt Adjustment for Ad Generation Based on User Feedback," in Proceedings of the 14th ACM International Conference on Web Search and Data Mining, 2021, pp. 93-101, doi: 10.1145/3437963.3441758.
T. Brown et al., "Language Models are Few-Shot Learners," arXiv preprint arXiv:2005.14165, 2020.
J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, "BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding," arXiv preprint arXiv:1810.04805, 2018.
Y. Liu, M. Zhang, and S. Ma, "Combining Automatic Metrics with Human Judgments for Quality Assessment of Generated Ad Content," in Proceedings of the 29th ACM International Conference on Information and Knowledge Management, 2020, pp. 2109-2116, doi: 10.1145/3340531.3411910.
V. Mnih et al., "Human-level control through deep reinforcement learning," Nature, vol. 518, no. 7540, pp. 529-533, 2015, doi: 10.1038/nature14236.
X. Wang, R. Zhang, Y. Sun, and J. Qi, "Deep Reinforcement Learning for Sponsored Search Real-time Bidding," in Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2018, pp. 1021-1030, doi: 10.1145/3219819.3219918.
X. Zhao, L. Zhang, Z. Ding, L. Xia, J. Tang, and D. Yin, "Recommendations with Negative Feedback via Pairwise Deep Reinforcement Learning," in Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2018, pp. 1040-1048, doi: 10.1145/3219819.3219886.
D. Yin, Y. Hu, J. Tang, T. Daly, M. Zhou, H. Ouyang, J. Chen, C. Kang, H. Deng, C. Nobata, J.-M. Langlois, and Y. Chang, "Ranking Relevance in Yahoo Search," in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, pp. 323-332, doi: 10.1145/2939672.2939677.
X. Zhang, J. Zhao, and Y. LeCun, "Character-level Convolutional Networks for Text Classification," in Proceedings of the 28th International Conference on Neural Information Processing Systems, 2015, pp. 649-657.
J. Azimi, R. Zhang, Y. Zhou, V. Navalpakkam, J. Mao, and X. Fern, "The Impact of Visual Appearance on User Response in Online Display Advertising," in Proceedings of the 21st International Conference on World Wide Web, 2012, pp. 457-458, doi: 10.1145/2187836.2187911.
A. Broder, P. Ciccolo, E. Gabrilovich, V. Josifovski, D. Metzler, L. Riedel, and J. Yuan, "Online Expansion of Rare Queries for Sponsored Search," in Proceedings of the 18th International Conference on World Wide Web, 2009, pp. 511-520, doi: 10.1145/1526709.1526778.
A. Radford, J. Wu, R. Child, D. Luan, D. Amodei, and I. Sutskever, "Language Models are Unsupervised Multitask Learners," OpenAI Blog, 2019. [Online]. Available: https://openai.com/blog/better-language-models/
A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, "Attention is All You Need," in Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017, pp. 6000-6010.
X. He, J. Pan, O. Jin, T. Xu, B. Liu, T. Xu, Y. Shi, A. Atallah, R. Herbrich, S. Bowers, and J. Q. Candela, "Practical Lessons from Predicting Clicks on Ads at Facebook," in Proceedings of the 8th International Workshop on Data Mining for Online Advertising, 2014, pp. 1-9, doi: 10.1145/2648584.2648589.
B. Liang, J. Huang, F. Liu, D. Wang, D. Dong, and Z. Xu, "Factorization Machines for Conversion Rate Prediction in Online Advertising," in Proceedings of the 27th ACM International Conference on Information and Knowledge Management, 2018, pp. 2109-2112, doi: 10.1145/3269206.3269308.
H. Cheng, and E. Cantú-Paz, "Personalized Click Prediction in Sponsored Search," in Proceedings of the 3rd ACM International Conference on Web Search and Data Mining, 2010, pp. 351-360, doi: 10.1145/1718487.1718531.
Y. Liu, J. Xu, X. He, Y. Yan, L. Shou, C. Chen, and P. Cui, "Joint Optimization of Creative and Audience Targeting for Online Advertising," in Proceedings of the 29th ACM International Conference on Information and Knowledge Management, 2020, pp. 2061-2068, doi: 10.1145/3340531.3411977.
X. Wang, R. Zhang, Y. Sun, and J. Qi, "Combating Selection Biases in Recommender Systems with a Few Unbiased Ratings," in Proceedings of the 13th International Conference on Web Search and Data Mining, 2020, pp. 427-435, doi: 10.1145/3336191.3371851.
S. Li, B. Wang, T. Xu, and L. Yang, "Real-Time Bidding by Reinforcement Learning in Display Advertising," in Proceedings of the 10th ACM International Conference on Web Search and Data Mining, 2017, pp. 661-670, doi: 10.1145/3018661.3018702.
S. Yuan, J. Wang, B. Chen, P. Mason, and S. Seljan, "An Empirical Study of Reserve Price Optimisation in Real-Time Bidding," in Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2014, pp. 1897-1906, doi: 10.1145/2623330.2623357.
C. Perlich, B. Dalessandro, R. Hook, O. Stitelman, T. Raeder, and F. Provost, "Bid Optimizing and Inventory Scoring in Targeted Online Advertising," in Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2012, pp. 804-812, doi: 10.1145/2339530.2339655.
B. Dalessandro, C. Perlich, O. Stitelman, and F. Provost, "Causally Motivated Attribution for Online Advertising," in Proceedings of the 6th International Workshop on Data Mining for Online Advertising and Internet Economy, 2012, pp. 1-9, doi: 10.1145/2351356.2351363.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Lav Kumar , Karan Khanna (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
