Collaborating Authors

Defining a machine learning problem


What we are looking at is a recommendation engine problem. Given the personal data you want to make the diet recommendation that are best suited for the person based on the data inserted.

Online shopping gets personal with Recommendations AI


With the continuing shift to digital, especially in the retail industry, ensuring a highly personalized shopping experience for online customers is crucial for establishing customer loyalty. In particular, product recommendations are an effective way to personalize the customer experience as they help customers discover products that match their tastes and preferences. Google has spent years delivering high-quality recommendations across our flagship products like YouTube and Google Search. Recommendations AI draws on that rich experience to give organizations a way to deliver highly personalized product recommendations to their customers at scale. Today, we are pleased to announce that Recommendations AI is now publicly available to all customers in beta.



We are a fast-growing and leading company in the personalized health space. We build software to help interpret peoples' genetics, lab tests and symptoms in order to give personalized health recommendations. Our primary goal is to give people the tools they need to live a healthier and better life We are a flat organization and prioritize efficiency We work as a team and every input and suggestion is taken into account, no matter who it comes from We thrive on open communication and dedication We are a meritocracy and people who show good abilities can move up in the organization fast. - With over 1.5 million visitors per month, SelfHacked is the best source of scientific information on supplements and health topics with integrity, no agenda or ideology. We strive for completeness and accuracy, and we work to make it accessible for everyone.

Making Personalized Recommendation through Conversation: Architecture Design and Recommendation Methods

AAAI Conferences

Due to popularity in texting and messaging, a recent advancement of deep learning technologies, a conversation-based interaction becomes an emerging user interface. While today’s conversation platforms offer basic conversation capabilities such as natural language understanding, entity extraction and simple dialogue management, there are still challenges in developing practical applications to support complex use cases using a dialogue system. In this paper, we highlight such challenges and share practical knowledge learned from our experiences on developing a leisure travel shopping application that combines a personalized recommendation system and a conversation system. Such efforts include a conversation design, extraction of user intents, communication of variables between a dialogue system and analytics engines, and dynamic user interface designs. In particular, we introduce our approach to overcome the unique challenges, understanding user's intent, when dialogue system met personalized recommendation system. Furthermore, we propose a semantic mapping as a novel method to utilize undefined user's preferences when producing recommended items. Finally, examples of recommendations based on natural language conversations are provided in order to exhibit how components in the overall architecture are seamlessly orchestrated. In general, our framework provides guiding principles and best practices on the implementation of task-oriented dialogue system connected with other components in the overall architecture.

Consumers Reports pulls Microsoft laptop recommendation

Boston Herald

Consumer Reports is pulling its recommendation of four Microsoft laptops after one of its surveys found that users were complaining about problems with the devices. The consumer advocacy group said Thursday that it can no longer recommend Microsoft laptops or tablets because of poor reliability compared to other brands. Microsoft said the findings don't accurately reflect Surface owners' "true experiences." The consumer group says Microsoft machines have performed well in laboratory testing. But a subscriber survey found start-up and freezing problems.