There's this odd feeling that starts at the back of the neck. It feels like the hairs are raising up slightly. The first time I felt it was in the mid-70s. I was in high school. I was sitting in front of an ASR-33 teletype machine and I hit something, probably the RE-TURN key. That's how it was spelled.

A well-designed recommender system can accurately capture the attributes of users and items, reflecting the unique preferences of individuals. Traditional recommendation techniques usually focus on modeling the singular type of behaviors between users and items. However, in many practical recommendation scenarios (e.g., social media, e-commerce), there exist multi-typed interactive behaviors in user-item relationships, such as click, tag-as-favorite, and purchase in online shopping platforms. Thus, how to make full use of multi-behavior information for recommendation is of great importance to the existing system, which presents challenges in two aspects that need to be explored: (1) Utilizing users' personalized preferences to capture multi-behavioral dependencies; (2) Dealing with the insufficient recommendation caused by sparse supervision signal for target behavior. In this work, we propose a Knowledge Enhancement Multi-Behavior Contrastive Learning Recommendation (KMCLR) framework, including two Contrastive Learning tasks and three functional modules to tackle the above challenges, respectively. In particular, we design the multi-behavior learning module to extract users' personalized behavior information for user-embedding enhancement, and utilize knowledge graph in the knowledge enhancement module to derive more robust knowledge-aware representations for items. In addition, in the optimization stage, we model the coarse-grained commonalities and the fine-grained differences between multi-behavior of users to further improve the recommendation effect. Extensive experiments and ablation tests on the three real-world datasets indicate our KMCLR outperforms various state-of-the-art recommendation methods and verify the effectiveness of our method.

Alexa, are there more layoffs coming, will they fire us all or make us return to office. Alexa: "I rather keep my mouth shut or risk being replaced by ChatGPT"

Faire is an online wholesale marketplace built on the belief that the future is local -- independent retailers around the globe are doing more revenue than Walmart and Amazon combined. At Faire, we're using the power of tech, data, and machine learning to connect this thriving community of entrepreneurs across the globe. Picture your favorite boutique in town -- we help them discover the best products from around the world to sell in their stores. With the right tools and insights, we believe that we can level the playing field so that small businesses everywhere can compete with these big box and e-commerce giants. By supporting the growth of independent businesses, Faire is driving positive economic impact in local communities, globally.

Today's customer expects the ability to engage with businesses through various communication channels like email, SMS, Push notifications, and in-app notifications when they have a question or need a problem resolved. SMS is one of the fastest growing communication channels, and we've seen that customers enjoy the ease and speed of texting for help versus traditional call channels. However, building an SMS system at scale to address millions of inquiries can be challenging for even the most advanced IT departments. Research also shows that customers prefer a personalized experience over a generic one, but using agents or employees to personalize millions of messages on a case-by-case basis is not practical. To solve this problem, we can use Amazon Pinpoint, AWS' multichannel communication service, to interact in personalized 2-way SMS messages with customers.

We're celebrating Earth Day 2022 from 4/22 through 4/29 with posts that highlight how to build, maintain, and refine your workloads for sustainability. AWS estimates that inference (the process of using a trained machine learning [ML] algorithm to make a prediction) makes up 90 percent of the cost of an ML model. Given with AWS you pay for what you use, we estimate that inference also generally equates to most of the resource usage within an ML lifecycle. In Part 3, our final piece in the series, we show you how to reduce the environmental impact of your ML workload once your model is in production. If you missed the first parts of this series, in Part 1, we showed you how to examine your workload to help you 1) evaluate the impact of your workload, 2) identify alternatives to training your own model, and 3) optimize data processing.

A central problem in multivariate forecasting is the need to forecast a large group of time series arranged in a natural hierarchical structure, such that time series at higher levels of the hierarchy are aggregates of time series at lower levels. For example, hierarchical time series are common in retail forecasting applications [Fildes et al., 2019], where the time series may capture retail sales of a company at different granularities such as item-level sales, category-level sales, and department-level sales. In electricity demand forecasting [Van Erven and Cugliari, 2015], the time series may correspond to electricity consumption at different granularities, starting with individual households, which could be progressively grouped into city-level, and then state-level consumption time-series. The hierarchical structure among the time series is usually represented as a tree, with leaf-level nodes corresponding to time series at the finest granularity, while higher-level nodes represent coarser-granularities and are obtained by aggregating the values from its children nodes. Since businesses usually require forecasts at various different granularities, the goal is to obtain accurate forecasts for time series at every level of the hierarchy. Furthermore, to ensure decisionmaking at different hierarchical levels are aligned, it is essential to generate predictions that are coherent [Hyndman et al., 2011] with respect to the hierarchy, that is, the forecasts of a parent time-series should be equal to the sum of forecasts of its children time-series.

Customer Service Chatbot: ChatGPT can be used to create a customer service chatbot that can provide customers with personalized answers to their questions and route them to the right resources. The chatbot can be trained to understand customer needs and provide timely responses to their queries. Online Shopping Assistant: ChatGPT can be used to create an online shopping assistant that can help customers find and purchase products from an online store. The chatbot can be trained to understand the customer's preferences and recommend products accordingly. Educational Chatbot: ChatGPT can be used to create an educational chatbot that can help students learn by providing personalized explanations to their queries.

Ankush Sabharwal, Founder & CEO of CoRover.ai, a human-centric conversational AI platform being used by 1 Billion users. Conversational AI chatbots are revolutionizing the way businesses interact with their customers. These AI-powered chatbots can understand and respond to customer queries in a natural and human-like manner, making the customer experience more efficient and personalized. Conversational AI started with click-based UI. From there it went to keyword-based search to AI/NLU-based intent classification and entry extractions, and now it has reached deep learning/NLG-based LLM/generative AI, which is the reason conversational AI is producing headlines today.

In many digital contexts such as online news and e-tailing with many new users and items, recommendation systems face several challenges: i) how to make initial recommendations to users with little or no response history (i.e., cold-start problem), ii) how to learn user preferences on items (test and learn), and iii) how to scale across many users and items with myriad demographics and attributes. While many recommendation systems accommodate aspects of these challenges, few if any address all. This paper introduces a Collaborative Filtering (CF) Multi-armed Bandit (B) with Attributes (A) recommendation system (CFB-A) to jointly accommodate all of these considerations. Empirical applications including an offline test on MovieLens data, synthetic data simulations, and an online grocery experiment indicate the CFB-A leads to substantial improvement on cumulative average rewards (e.g., total money or time spent, clicks, purchased quantities, average ratings, etc.) relative to the most powerful extant baseline methods.