In this work, we propose to improve long-term user engagement in a recommender system from the perspective of sequential decision optimization, where users' click and return behaviors are directly modeled for online optimization. A bandit-based solution is formulated to balance three competing factors during online learning, including exploitation for immediate click, exploitation for expected future clicks, and exploration of unknowns for model estimation. We rigorously prove that with a high probability our proposed solution achieves a sublinear upper regret bound in maximizing cumulative clicks from a population of users in a given period of time, while a linear regret is inevitable if a user's temporal return behavior is not considered when making the recommendations. Extensive experimentation on both simulations and a large-scale real-world dataset collected from Yahoo frontpage news recommendation log verified the effectiveness and significant improvement of our proposed algorithm compared with several state-of-the-art online learning baselines for recommendation.
Deep Learning for Online Display Advertising User Clicks and Interests Prediction
In this paper, we propose a deep learning based framework for user interest modeling and click prediction. Our goal is to accurately predict (1) the probability that a user clicks on an ad, and (2) the probability that a user clicks a specify type of campaign ad. To achieve the goal, we collect page information displayed to users as a temporal sequence, and use long-term-short-term memory (LSTM) network to learn latent features representing user interests. Experiments and comparisons on real-world data shows that, compared to existing static set based approaches, considering sequences and temporal variance of user requests results in an improvement in performance ad click prediction and campaign specific ad click prediction.
- Award ID(s):
- Publication Date:
- NSF-PAR ID:
- Journal Name:
- Proc. of the 3rd International Joint Conference on Web and Big Data (APWeb-WAIM 2019)
- Sponsoring Org:
- National Science Foundation
More Like this
Online advertising, as a vast market, has gained significant attention in various platforms ranging from search engines, third-party websites, social media, and mobile apps. The prosperity of online campaigns is a challenge in online marketing and is usually evaluated by user response through different metrics, such as clicks on advertisement (ad) creatives, subscriptions to products, purchases of items, or explicit user feedback through online surveys. Recent years have witnessed a significant increase in the number of studies using computational approaches, including machine learning methods, for user response prediction. However, existing literature mainly focuses on algorithmic-driven designs to solve specific challenges, and no comprehensive review exists to answer many important questions. What are the parties involved in the online digital advertising eco-systems? What type of data are available for user response prediction? How do we predict user response in a reliable and/or transparent way? In this survey, we provide a comprehensive review of user response prediction in online advertising and related recommender applications. Our essential goal is to provide a thorough understanding of online advertising platforms, stakeholders, data availability, and typical ways of user response prediction. We propose a taxonomy to categorize state-of-the-art user response prediction methods, primarily focusing on themore »
In this paper, a two-level deep learning framework is presented to model human information foraging behavior with search engines. A recurrent neural network architecture is designed using LSTM as the base unit to explicitly consider the temporal and spatial dependencies of information scents, the key concept in Information Foraging Theory. The target is to predict several major search behaviors, such as query abandonment, query reformulation, number of clicks, and information gain. The memory capability and the sequence structure of LSTM allow to naturally mimic not only what users are perceiving and performing at the moment but also what they have seen and learned from the past during the search dynamics. The promising results indicate that our information scent models with different input variations were better, compared to the state-of-the art neural click models, at predicting some search behaviors. When incorporating the knowledge from a previous query in the same search session, the prediction of current query abandonment, pagination, and information gain has been improved. Compared to the well known neural click models that model search behaviors under a single search query thread, this study takes a broader view to consider an entire search session which may contain multiple queries. Moremore »
Obeid, Iyad Selesnick (Ed.)Electroencephalography (EEG) is a popular clinical monitoring tool used for diagnosing brain-related disorders such as epilepsy . As monitoring EEGs in a critical-care setting is an expensive and tedious task, there is a great interest in developing real-time EEG monitoring tools to improve patient care quality and efficiency . However, clinicians require automatic seizure detection tools that provide decisions with at least 75% sensitivity and less than 1 false alarm (FA) per 24 hours . Some commercial tools recently claim to reach such performance levels, including the Olympic Brainz Monitor  and Persyst 14 . In this abstract, we describe our efforts to transform a high-performance offline seizure detection system  into a low latency real-time or online seizure detection system. An overview of the system is shown in Figure 1. The main difference between an online versus offline system is that an online system should always be causal and has minimum latency which is often defined by domain experts. The offline system, shown in Figure 2, uses two phases of deep learning models with postprocessing . The channel-based long short term memory (LSTM) model (Phase 1 or P1) processes linear frequency cepstral coefficients (LFCC)  features from each EEGmore »
Given the importance of fresh water, we investigated undergraduate students’ understanding of water flow and its consequences. We probed introductory geology students’ pre-instruction knowledge using a classroom management system at two large research-intensive universities. Open-ended clicker questions, where students click directly on diagrams using their smart device (e.g., cell phone, tablet) to respond, probed students’ predictions about: (1) groundwater movement and (2) velocity and erosion in a river channel. Approximately one-third of students correctly identified groundwater flow as having lateral and vertical components; however, the same number of students identified only vertical components to flow despite the diagram depicting enough topographic gradient for lateral flow. For rivers depicted as having a straight channel, students correctly identified zones of high velocity. However, for curved river channels, students incorrectly identified the inside of the bend as the location of greatest erosion and highest velocity. Systematic errors suggest that students have mental models of water flow that are not consistent with fluid dynamics. The use of students’ open-ended clicks to reveal common errors provided an efficient tool to identify conceptual challenges associated with the complex spatial and temporal processes that govern water movement in the Earth system.