Marketing Budget Allocation with Offline Constrained Deep Reinforcement Learning

Cai, Tianchi; Jiang, Jiyan; Zhang, Wenpeng; Zhou, Shiji; Xierui, Song,; Yu, Li; Gu, Lihong; Zeng, Xiaodong; Gu, Jinjie; Zhang, Guannan

doi:10.1145/3539597.3570486

Cited by 3 publications

(2 citation statements)

References 36 publications

(72 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…"Marketing Budget Allocation with Offline Constrained Deep Reinforcement Learning" [3] T. Cai et al, "Marketing budget allocation with offline constrained deep reinforcement learning," This research paper explores using Reinforcement Learning (RL) for budget allocation in online marketing campaigns, especially for user acquisition and retention. It highlights the limitations of traditional methods relying on immediate user responses (e.g., coupon redemption).…”

Section: 17mentioning

confidence: 99%

Budgetting Analysis Using Machine Learning

2024

IJSREM

View full text Add to dashboard Cite

In an era characterized by unparalleled technological progress and pervasive digital integration, the amalgamation of machine learning and mobile applications has instigated a significant transformation in the realm of financial management. This report embarks on a thorough exploration of this revolutionary convergence, elucidating its impact on budget analysis and forecasting, while also laying the groundwork for a future distinguished by heightened fiscal oversight and informed decision-making. The evolution of budget management and financial forecasting has been intricately linked to the ascent of digital technology. As the intricacies of financial challenges confronting individuals, enterprises, and governments continue to evolve, there arises an increasing need for innovative solutions capable of adapting to diverse financial profiles. At the heart of this transformative shift lies the fusion of Flutter, a versatile and user-friendly mobile app development framework, with the predictive capabilities of machine learning, heralding a paradigmatic shift in the domain of budget analysis. This report offers a comprehensive exploration of our project's multifaceted dimensions. From its conceptualization and rationale to the intricate technical architecture and methodologies underpinning its functionality, each aspect is meticulously examined. Throughout this captivating journey, we delve deeply into the realm of data-driven financial prediction, where machine learning algorithms dissect historical spending patterns, illuminating potential future financial trajectories. The Flutter application, meticulously designed to serve as an intuitive gateway to personalized financial insights and effective budget management, occupies a central role in this endeavor. It epitomizes accessibility and ease of use, empowering users from diverse backgrounds to harness the power of data-driven fiscal decision-making. Beyond the technological innovations, this report underscores the paramount importance of ethical considerations. In an era where data privacy and algorithmic fairness are of utmost concern, we adopt a proactive stance in ensuring that our project adheres to the highest ethical standards. Our endeavor transcends mere innovation; it is a commitment to shaping a more inclusive and responsible financial future’s.

show abstract

Section: 17mentioning

confidence: 99%

Budgetting Analysis Using Machine Learning

2024

IJSREM

View full text Add to dashboard Cite

show abstract

“…It learns desired behaviors from interactions with an environment to maximize the long-term cumulative reward [1,32]. Compared to conventional methods such as collaborative filtering [22] and deep learning-based methods [10,18,43], RL is capable of handling partial feedback and optimizing long-term experience, hence it is promising in many real-world recommendation scenarios [4,5,39,42].…”

Section: Introductionmentioning

confidence: 99%

Model-free Reinforcement Learning with Stochastic Reward Stabilization for Recommender Systems

Cai¹,

Shenliao²,

Jiang³

et al. 2023

Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval

Self Cite

View full text Add to dashboard Cite

Model-free RL-based recommender systems have recently received increasing research attention due to their capability to handle partial feedback and long-term rewards. However, most existing research has ignored a critical feature in recommender systems: one user's feedback on the same item at different times is random. The stochastic rewards property essentially differs from that in classic RL scenarios with deterministic rewards, which makes RL-based recommender systems much more challenging. In this paper, we first demonstrate in a simulator environment where using direct stochastic feedback results in a significant drop in performance. Then to handle the stochastic feedback more efficiently, we design two stochastic reward stabilization frameworks that replace the direct stochastic feedback with that learned by a supervised model. Both frameworks are model-agnostic, i.e., they can effectively utilize various supervised models. We demonstrate the superiority of the proposed frameworks over different RL-based recommendation baselines with extensive experiments on a recommendation simulator as well as an industrial-level recommender system. CCS CONCEPTS• Computing methodologies → Sequential decision making.

show abstract

Report on the 16th ACM International Conference on Web Search and Data Mining (WSDM 2023)

Lauw,

Chua,

et al. 2023

SIGIR Forum

View full text Add to dashboard Cite

The 16th ACM International Conference on Web Search and Data Mining (WSDM 2023) was held in Singapore. It was held as in-person conference that also featured rich virtual elements. This brief report provides an overview of WSDM 2023 with organization and program details and statistics from Conference Chairs and Program Committee Chairs, as well as a message from the WSDM Steering Committee Chair. Date: 27 February-3 March 2023. Website: https://www.wsdm-conference.org/2023.

show abstract

Marketing Budget Allocation with Offline Constrained Deep Reinforcement Learning

Cited by 3 publications

References 36 publications

Budgetting Analysis Using Machine Learning

Budgetting Analysis Using Machine Learning

Model-free Reinforcement Learning with Stochastic Reward Stabilization for Recommender Systems

Report on the 16th ACM International Conference on Web Search and Data Mining (WSDM 2023)

Contact Info

Product

Resources

About