"Receiving proactive service leads to a 9% increase in a customer's value enhancement score," said Eric Keller, senior research director in the Gartner Customer Service & Support practice. The goal of customer success is to ensure that your client receives measurable value in a reasonable time frame with the help of CCAI.

Large-scale online recommendation systems must facilitate the allocation of a limited number of items among competing users while learning their preferences from user feedback. As a principled way of incorporating market constraints and user incentives in the design, we consider our objectives to be two-fold: maximal social welfare with minimal instability. To maximize social welfare, our proposed framework enhances the quality of recommendations by exploring allocations that optimistically maximize the rewards. To minimize instability, a measure of users' incentives to deviate from recommended allocations, the algorithm prices the items based on a scheme derived from the Walrasian equilibria. Though it is known that these equilibria yield stable prices for markets with known user preferences, our approach accounts for the inherent uncertainty in the preferences and further ensures that the users accept their recommendations under offered prices. To the best of our knowledge, our approach is the first to integrate techniques from combinatorial bandits, optimal resource allocation, and collaborative filtering to obtain an algorithm that achieves sub-linear social welfare regret as well as sub-linear instability. Empirical studies on synthetic and real-world data also demonstrate the efficacy of our strategy compared to approaches that do not fully incorporate all these aspects.

Business processes that involve AI-powered automation have been gaining importance and market share in recent years. These business processes combine the characteristics of classical business process management, goal-driven chatbots, conversational recommendation systems, and robotic process automation. In the new context, prescriptive process monitoring demands innovative approaches. Unfortunately, data logs from these new processes are still not available in the public domain. We describe the main challenges in this new domain and introduce a synthesized dataset that is based on an actual use case of intelligent process automation with chatbot orchestration. Using this dataset, we demonstrate crowd-wisdom and goal-driven approaches to prescriptive process monitoring.

Today, recommender systems have played an increasingly important role in shaping our experiences of digital environments and social interactions. However, as recommender systems become ubiquitous in our society, recent years have also witnessed significant fairness concerns for recommender systems. Specifically, studies have shown that recommender systems may inherit or even amplify biases from historical data, and as a result, provide unfair recommendations. To address fairness risks in recommender systems, most of the previous approaches to date are focused on modifying either the existing training data samples or the deployed recommender algorithms, but unfortunately with limited degrees of success. In this paper, we propose a new approach called fair recommendation with optimized antidote data (FairRoad), which aims to improve the fairness performances of recommender systems through the construction of a small and carefully crafted antidote dataset. Toward this end, we formulate our antidote data generation task as a mathematical optimization problem, which minimizes the unfairness of the targeted recommender systems while not disrupting the deployed recommendation algorithms. Extensive experiments show that our proposed antidote data generation algorithm significantly improve the fairness of recommender systems with a small amounts of antidote data.

Bixby is an intelligent personal assistant which is only available as a built-in application on Samsung flagship devices and wearables. This application uses Natural Language Processing and Knowledge-Based AI to perform tasks on these devices using multimodal inputs and additional contextual information, including but not limited to making phone calls, sending text messages, setting up meetings, opening apps, setting alarms and timers, getting directions, answering general questions, providing information about restaurants and other businesses, etc. The Natural Language Processing and Knowledge-Based AI team aims to create a delightful experience for Bixby customers by making Bixby understand the intent behind any type of request quickly and accurately, and to proactively adapt to the users' needs. You will collaborate closely with experts in Machine Learning, Natural Language Processing and Knowledge-Based AI, and contribute to advancing the state of the art in virtual assistants. As a Senior Knowledge-Based AI Engineer you will primarily focus on building the Natural Language Understanding and Proactive Behavior platform for Bixby by working with Product Managers / Subject Matter Experts, Lab Leaders, Linguistic Experts, brainstorm different ideas, research, build POCs and propose solutions that cater to the broader business needs.

It took a couple of months, but the first smart home devices to support the Matter standard are finally ready. As promised in November, Eve Systems is updating the Eve Energy plug and two sensors, the Eve Door & Window and Eve Motion, with Matter support. The free firmware lets the previously HomeKit-only hardware talk to any controller that supports the new technology, including Samsung's SmartThings app as well as upcoming support through Amazon Alexa and Google Home. As The Verge notes, the update currently requires the not-yet-official iOS and iPadOS 16.2 upgrades that could arrive this week, and you'll have to enlist in an early access program. You won't need Apple products for much longer, though.

For researchers leveraging Large-Language Models (LLMs) in the generation of training datasets, especially for conversational recommender systems - the absence of robust evaluation frameworks has been a long-standing problem Peng et al. (2017). The efficiency brought about by LLMs in the data generation phase is impeded during the process of evaluation of the generated data, since it generally requires human-raters to ensure that the data generated is of high quality and has sufficient diversity. Since the quality of training data is critical for downstream applications, it is important to develop metrics that evaluate the quality holistically and identify biases. In this paper, we present a framework that takes a multi-faceted approach towards evaluating datasets produced by generative models and discuss the advantages and limitations of various evaluation methods.

Self-attentive transformer models have recently been shown to solve the next item recommendation task very efficiently. The learned attention weights capture sequential dynamics in user behavior and generalize well. Motivated by the special structure of learned parameter space, we question if it is possible to mimic it with an alternative and more lightweight approach. We develop a new tensor factorization-based model that ingrains the structural knowledge about sequential data within the learning process. We demonstrate how certain properties of a self-attention network can be reproduced with our approach based on special Hankel matrix representation. The resulting model has a shallow linear architecture and compares competitively to its neural counterpart.

Online personalized recommendation services are generally hosted in the cloud where users query the cloud-based model to receive recommended input such as merchandise of interest or news feed. State-of-the-art recommendation models rely on sparse and dense features to represent users' profile information and the items they interact with. Although sparse features account for 99% of the total model size, there was not enough attention paid to the potential information leakage through sparse features. These sparse features are employed to track users' behavior, e.g., their click history, object interactions, etc., potentially carrying each user's private information. Sparse features are represented as learned embedding vectors that are stored in large tables, and personalized recommendation is performed by using a specific user's sparse feature to index through the tables. Even with recently-proposed methods that hides the computation happening in the cloud, an attacker in the cloud may be able to still track the access patterns to the embedding tables. This paper explores the private information that may be learned by tracking a recommendation model's sparse feature access patterns. We first characterize the types of attacks that can be carried out on sparse features in recommendation models in an untrusted cloud, followed by a demonstration of how each of these attacks leads to extracting users' private information or tracking users by their behavior over time.

Exploiting social relations in recommendation works well because of the effects of social homophily [61] and social influence [60]: (1) social homophily indicates that a user tends to connect herself to other users with similar attributes and preferences, and (2) social influence indicates that users with direct or indirect relations tend to influence each other to make themselves become more similar. Accordingly, SocialRS can effectively mitigate the data sparsity problem by exploiting social neighbors to capture the preferences of a sparsely interacting user. Literature has shown that SocialRS can be applied successfully in various recommendation domains (e.g., product [101, 103], music [116-118], location [39, 72, 100], and image [86, 99, 102]), thereby improving user satisfaction. Furthermore, techniques and insights explored from SocialRS can also be exploited in real-world applications other than recommendations. For instance, García-Sánchez et al. [20] leveraged SocialRS to design a decision-making system for marketing (e.g., advertisement), while Gasparetti et al. [21] analyzed SocialRS in terms of community detection. Motivated by such wide applicability, there has been an increasing interest in research on developing accurate 40 SocialRS models. In the early days, research focused on matrix factorization (MF) techniques [28, 54-20 57, 84, 112].