Demand Estimation with Text and Image Data


Book Description

We propose a demand estimation method that allows researchers to estimate substitution patterns from unstructured image and text data. We first employ a series of machine learning models to measure product similarity from products' images and textual descriptions. We then estimate a nested logit model with product-pair specific nesting parameters that depend on the image and text similarities between products. Our framework does not require collecting product attributes for each category and can capture product similarity along dimensions that are hard to account for with observed attributes. We apply our method to a dataset describing the behavior of Amazon shoppers across several categories and show that incorporating texts and images in demand estimation helps us recover a flexible cross-price elasticity matrix.




Hands-On Machine Learning with Azure


Book Description

Implement machine learning, cognitive services, and artificial intelligence solutions by leveraging Azure cloud technologies Key FeaturesLearn advanced concepts in Azure ML and the Cortana Intelligence Suite architectureExplore ML Server using SQL Server and HDInsight capabilitiesImplement various tools in Azure to build and deploy machine learning modelsBook Description Implementing Machine learning (ML) and Artificial Intelligence (AI) in the cloud had not been possible earlier due to the lack of processing power and storage. However, Azure has created ML and AI services that are easy to implement in the cloud. Hands-On Machine Learning with Azure teaches you how to perform advanced ML projects in the cloud in a cost-effective way. The book begins by covering the benefits of ML and AI in the cloud. You will then explore Microsoft’s Team Data Science Process to establish a repeatable process for successful AI development and implementation. You will also gain an understanding of AI technologies available in Azure and the Cognitive Services APIs to integrate them into bot applications. This book lets you explore prebuilt templates with Azure Machine Learning Studio and build a model using canned algorithms that can be deployed as web services. The book then takes you through a preconfigured series of virtual machines in Azure targeted at AI development scenarios. You will get to grips with the ML Server and its capabilities in SQL and HDInsight. In the concluding chapters, you’ll integrate patterns with other non-AI services in Azure. By the end of this book, you will be fully equipped to implement smart cognitive actions in your models. What you will learnDiscover the benefits of leveraging the cloud for ML and AIUse Cognitive Services APIs to build intelligent botsBuild a model using canned algorithms from Microsoft and deploy it as a web serviceDeploy virtual machines in AI development scenariosApply R, Python, SQL Server, and Spark in AzureBuild and deploy deep learning solutions with CNTK, MMLSpark, and TensorFlowImplement model retraining in IoT, Streaming, and Blockchain solutionsExplore best practices for integrating ML and AI functions with ADLA and logic appsWho this book is for If you are a data scientist or developer familiar with Azure ML and cognitive services and want to create smart models and make sense of data in the cloud, this book is for you. You’ll also find this book useful if you want to bring powerful machine learning services into your cloud applications. Some experience with data manipulation and processing, using languages like SQL, Python, and R, will aid in understanding the concepts covered in this book







Large-scale Demand Estimation with Search Data


Book Description

Many online markets are characterized by sellers that stock large numbers of products and sell each product infrequently. At the same time, consumer browsing information is typically tracked by online retailers and is much more abundant than purchase data. We propose a demand model that caters to this type of setting. Our approach, which is based on search and purchase data, is computationally light and allows for flexible substitution patterns. We apply the model to a data set containing browsing and purchase information from a retailer stocking over 500 products, recover the elasticity matrix, and solve for optimal prices for the entire assortment.




The Elements of Joint Learning and Optimization in Operations Management


Book Description

This book examines recent developments in Operations Management, and focuses on four major application areas: dynamic pricing, assortment optimization, supply chain and inventory management, and healthcare operations. Data-driven optimization in which real-time input of data is being used to simultaneously learn the (true) underlying model of a system and optimize its performance, is becoming increasingly important in the last few years, especially with the rise of Big Data.




Computational Collective Intelligence


Book Description

This two-volume set (LNAI 9875 and LNAI 9876) constitutes the refereed proceedings of the 8th International Conference on Collective Intelligence, ICCCI 2016, held in Halkidiki, Greece, in September 2016. The 108 full papers presented were carefully reviewed and selected from 277 submissions. The aim of this conference is to provide an internationally respected forum for scientific research in the computer-based methods of collective intelligence and their applications in (but not limited to) such fields as group decision making, consensus computing, knowledge integration, semantic web, social networks and multi-agent systems.




Demand Estimation with Machine Learning and Model Combination


Book Description

We survey and apply several techniques from the statistical and computer science literature to the problem of demand estimation. We derive novel asymptotic properties for several of these models. To improve out-of-sample prediction accuracy and obtain parametric rates of convergence, we propose a method of combining the underlying models via linear regression. Our method has several appealing features: it is robust to a large number of potentially-collinear regressors; it scales easily to very large data sets; the machine learning methods combine model selection and estimation; and the method can flexibly approximate arbitrary non-linear functions, even when the set of regressors is high dimensional and we also allow for fixed effects. We illustrate our method using a standard scanner panel data set to estimate promotional lift and find that our estimates are considerably more accurate in out of sample predictions of demand than some commonly used alternatives. While demand estimation is our motivating application, these methods are likely to be useful in other microeconometric problems.




Intelligent Computer Vision and Image Processing: Innovation, Application, and Design


Book Description

Innovations in computer vision technology continue to advance the applications and design of image processing and its influence on multimedia applications. Intelligent Computer Vision and Image Processing: Innovation, Application, and Design provides methods and research on various disciplines related to the science and technology of machines. This reference source is essential for academicians, researchers, and practitioners interested in the latest developments and innovations in computer science, education, and security.







Open Data and Energy Analytics


Book Description

Open data and policy implications coming from data-aware planning entail collection and pre- and postprocessing as operations of primary interest. Before these steps, making data available to people and their decision-makers is a crucial point. Referring to the relationship between data and energy, public administrations, governments, and research bodies are promoting the construction of reliable and robust datasets to pursue policies coherent with the Sustainable Development Goals, as well as to allow citizens to make informed choices. Energy engineers and planners must provide the simplest and most robust tools to collect, process, and analyze data in order to offer solid data-based evidence for future projections in building, district, and regional systems planning. This Special Issue aims at providing the state-of-the-art on open-energy data analytics; its availability in the different contexts, i.e., country peculiarities; and its availability at different scales, i.e., building, district, and regional for data-aware planning and policy-making. For all the aforementioned reasons, we encourage researchers to share their original works on the field of open data and energy analytics. Topics of primary interest include but are not limited to the following: 1. Open data and energy sustainability; 2. Open data science and energy planning; 3. Open science and open governance for sustainable development goals; 4. Key performance indicators of data-aware energy modelling, planning, and policy; 5. Energy, water, and sustainability database for building, district, and regional systems; 6. Best practices and case studies.