Related papers: Mini-Game Lifetime Value Prediction in WeChat
Accurately predicting watch time is crucial for optimizing recommendations and user experience in short video platforms. However, existing methods that estimate a single average watch time often fail to capture the inherent uncertainty in…
Reinforcement learning from human feedback (RLHF) has demonstrated great promise in aligning large language models (LLMs) with human preference. Depending on the availability of preference data, both online and offline RLHF are active areas…
The rapid expansion of video game production necessitates the development of effective advertising and recommendation systems for online game platforms. Recommending and advertising games to users hinges on capturing their interest in…
Generating accurate and reliable sales forecasts is crucial in the E-commerce business. The current state-of-the-art techniques are typically univariate methods, which produce forecasts considering only the historical sales data of a single…
A key concern for AI safety remains understudied in the machine learning (ML) literature: how can we ensure users of ML models do not leverage predictions on incorrect personal data to harm others? This is particularly pertinent given the…
Large Language Models (LLMs) are increasingly applied to forecasting. To evaluate this capability while mitigating pre-training data contamination, several living benchmarks have been proposed. However, existing benchmarks either lack the…
Online Real-Time Bidding (RTB) is a complex auction game among which advertisers struggle to bid for ad impressions when a user request occurs. Considering display cost, Return on Investment (ROI), and other influential Key Performance…
In this paper, we explore how directly pretraining a value model simplifies and stabilizes reinforcement learning from human feedback (RLHF). In reinforcement learning, value estimation is the key to policy optimization, distinct from…
With increasing game size, a problem of computational complexity arises. This is especially true in real world problems such as in social systems, where there is a significant population of players involved in the game, and the complexity…
In video recommendation, a critical component that determines the system's recommendation accuracy is the watch-time prediction module, since how long a user watches a video directly reflects personalized preferences. One of the key…
Predicting lead close rates is one of the most problematic tasks in the lead generation industry. In most cases, the only available data on the prospect is the self-reported information inputted by the user on the lead form and a few other…
The video game industry is larger than both the film and music industries combined. Recommender systems for video games have received relatively scant academic attention, despite the uniqueness of the medium and its data. In this paper, we…
Latent variable models have been playing a central role in psychometrics and related fields. In many modern applications, the inference based on latent variable models involves one or several of the following features: (1) the presence of…
Vision Language Models (VLMs) struggle with long-form videos due to the quadratic complexity of attention mechanisms. We propose Language-Guided Temporal Token Pruning (LGTTP), which leverages temporal cues from queries to adaptively prune…
Longitudinal targeted maximum likelihood estimation (LTMLE) has very rarely been used to estimate dynamic treatment effects in the context of time-dependent confounding affected by prior treatment when faced with long follow-up times,…
Problem definition: Most of the display advertising inventory is sold through real-time auctions. The participants of these auctions are typically bidders (Google, Criteo, RTB House, Trade Desk for instance) who participate on behalf of…
Advertising is critical to many online e-commerce platforms such as e-Bay and Amazon. One of the important signals that these platforms rely upon is the click-through rate (CTR) prediction. The recent popularity of multi-modal sharing…
We study a finite-horizon dynamic pricing problem for event tickets with limited inventory and time-varying demand. The central practical difficulty is that the total demand function $L(t)$ is not observed directly and must be estimated…
Advertisement (abbreviated ad) options are a recent development in online advertising. Simply, an ad option is a first look contract in which a publisher or search engine grants an advertiser a right but not obligation to enter into…
Large language model (LLM) agents are increasingly equipped with memory, which are stored experience and reusable guidance that can improve task-solving performance. Recent \emph{self-evolving} systems update memory based on interaction…