We use learning to rank, sequence-based recommendation models, content or behavior representation-based algorithms, and collaborative filtering algorithms too. After the customer browses around, searching for hotels in city A, B or C, a substantial portion search for a single hotel and look at the responses/price/content to review. For such "direct hotel search" scenarios, it is prudent to show a few alternatives as well, for customers to compare and contrast them. More important if alternative hotels can bring higher value preposition to the business or to the customer (for ex., better service/value for same price). In this scenario, one could recommend hotels similar to the pivot hotel user has searched.

Over the last couple of years, powerful deep learning methods have emerged to build industrial scale natural language understanding applications. The first wave of deep learning models employed pre-trained word embeddings (word2vec or GloVe) to initialize the first layer of a neural network followed by a task specific model trained using labelled data. The next wave of deep learning architectures (ELMo, ULMFiT, BERT) showed how to learn contextual word embeddings from massive amounts of unlabelled text data and then transfer this information to a wide variety of downstream tasks such as sentiment analysis, question answering etc. with limited amounts of labelled data. This approach is quite relevant for industrial settings where obtaining large amounts of labelled data is expensive. In this hands on tutorial, we will cover the important concepts behind recent developments such as word embeddings, sequence to sequence models, attention mechanism, contextual word embeddings, transfer learning and probing embeddings.

Global online etailer Amazon is just about to change the way people shop for groceries. Amazon recently announced the beta programme for Amazon Go, a store where there are no checkout lines. Amazon has made use of technologies like machine learning, sensors and deep learning to allow buyers this experience. The 1,800 square feet store in Seattle is changing the way we do our grocery shopping, and will be open to public in early 2017. There is no clarity about how Amazon intends to roll this out or if it will ever come to India, but use of technologies like artificial intelligence (AI), cognitive learning, chatbots and others is changing our shopping experience.