We revisit the interest of classical statistical techniques for sales forecasting like exponential smoothing and extensions thereof (as Holt's linear trend method). We do so by considering ensemble forecasts, given by several instances of these classical techniques tuned with different (sets of) parameters, and by forming convex combinations of the elements of ensemble forecasts over time, in a robust and sequential manner. The machine-learning theory behind this is called "robust online aggregation", or "prediction with expert advice", or "prediction of individual sequences" (see Cesa-Bianchi and Lugosi, 2006). We apply this methodology to a hierarchical data set of sales provided by the e-commerce company Cdiscount and output forecasts at the levels of subsubfamilies, subfamilies and families of items sold, for various forecasting horizons (up to 6-week-ahead). The performance achieved is better than what would be obtained by optimally tuning the classical techniques on a train set and using their forecasts on the test set. The performance is also good from an intrinsic point of view (in terms of mean absolute percentage of error). While getting these better forecasts of sales at the levels of subsubfamilies, subfamilies and families is interesting per se, we also suggest to use them as additional features when forecasting demand at the item level.

Hierarchical forecasting methods have been widely used to support aligned decision-making by providing coherent forecasts at different aggregation levels. Traditional hierarchical forecasting approaches, such as the bottom-up and top-down methods, focus on a particular aggregation level to anchor the forecasts. During the past decades, these have been replaced by a variety of linear combination approaches that exploit information from the complete hierarchy to produce more accurate forecasts. However, the performance of these combination methods depends on the particularities of the examined series and their relationships. This paper proposes a novel hierarchical forecasting approach based on machine learning that deals with these limitations in three important ways. First, the proposed method allows for a non-linear combination of the base forecasts, thus being more general than the linear approaches. Second, it structurally combines the objectives of improved post-sample empirical forecasting accuracy and coherence. Finally, due to its non-linear nature, our approach selectively combines the base forecasts in a direct and automated way without requiring that the complete information must be used for producing reconciled forecasts for each series and level. The proposed method is evaluated both in terms of accuracy and bias using two different data sets coming from the tourism and retail industries. Our results suggest that the proposed method gives superior point forecasts than existing approaches, especially when the series comprising the hierarchy are not characterized by the same patterns.

AWS DeepComposer is an educational AWS service that teaches generative AI and uses Generative Adversarial Networks (GANs) to transform a melody that you provide into a completely original song. With AWS DeepComposer, you can use one of the pre-trained music genre models (such as Jazz, Rock, Pop, Symphony, or Jonathan-Coulton) or train your own. As a part of training your custom music genre model, you store your music data files in NumPy objects. This post accompanies the training steps in Lab 2 – Train a custom GAN model on GitHub and demonstrates how to convert your MIDI files to the proper training format for AWS DeepComposer. For this use case, you use your own MIDI files to train a Reggae music genre model.

Through the centuries, human civilizations have undergone periodic leaps in technology. From steam to electricity to computing, societies have made radical shifts as new ways of doing things have transformed how we work. We are now in what's been deemed the Fourth Industrial Revolution, an era of digital transformation that will forever change the way we work, and the way organizations operate. In today's world, technological advances such as automation, robotics and artificial intelligence – allow businesses to continue to grow and remain competitive. It has become clear that the organization of the future will be driven by the opportunities these technologies create.

In the paper, a problem of forecasting promotion efficiency is raised. The authors propose a new approach, using the gradient boosting method for this task. Six performance indicators are introduced to capture the promotion effect. For each of them, within predefined groups of products, a model was trained. A description of using these models for forecasting and optimising promotion efficiency is provided. Data preparation and hyperparameters tuning processes are also described. The experiments were performed for three groups of products from a large grocery company.

In January, my coworker received a peculiar email. The message, which she forwarded to me, was from a handful of corporate Walmart employees calling themselves the "Concerned Home Office Associates." While it's not unusual for journalists to receive anonymous tips, they don't usually come with their own slickly produced videos. The employees said they were "past their breaking point," with Everseen, a small artificial intelligence firm based in Cork, Ireland, whose technology Walmart began using in 2017. Walmart uses Everseen in thousands of stores to prevent shoplifting at registers and self-checkout kiosks.

CVS Health will try delivering prescriptions with self-driving vehicles in a test that begins next month. The drugstore chain said Thursday that it will partner with the Silicon Valley robotics company Nuro to deliver medicines and other products to customers near a Houston-area store. A CVS spokesman said the prescriptions will routinely be delivered within an hour of being ordered. Customers will have to confirm their identity in order to unlock their delivery after the vehicle arrives. Nuro has previously started partnerships to test the delivery of pizzas for Domino's or groceries for Kroger, also in the Houston area.

CVS Health will try delivering prescriptions with self-driving vehicles in a test that begins next month. The drugstore chain said Thursday that it will partner with the Silicon Valley robotics company Nuro to deliver medicines and other products to customers near a Houston-area store. A CVS spokesman said the prescriptions will routinely be delivered within an hour of being ordered. Customers will have to confirm their identity in order to unlock their delivery after the vehicle arrives. Nuro has previously started partnerships to test the delivery of pizzas for Domino's or groceries for Kroger, also in the Houston area.

As more online brands look for ways to move beyond third-party cookies as a way of gaining more direct insights about their users and customers, a startup that has developed a platform to help them has raised a big round of funding. Bluecore, a marketing technology firm that uses data gained from direct marketing like email, social media, site activity and combines that with machine learning to make better predictions about who might want to buy what among its customers, is today announcing that it has raised $50 million. The funding will be used to build the next generation of the Bluecore platform, expected later this year, which will tap into aggregated engagement data (but not actual browsing individuals) from "hundreds" of brands, which customers can combine with their own first-party data -- based on consent-based, first-party customer IDs -- to develop better targeting insights. "There are a lot of systems that focus on customer data and transactional data but no system that focuses on the product and product catalogue, which we think is the key asset," said Fayez Mohamood, the co-founder and CEO, in an interview. He says that the company manages over 200 million products and SKUs, second only to Amazon's and bigger than Walmart's, that companies can matches with consumer identities (from email and other direct channels).

At re:Invent 2019, AWS shared the fastest training times on the cloud for two popular machine learning (ML) models: BERT (natural language processing) and Mask-RCNN (object detection). To train BERT in 1 hour, we efficiently scaled out to 2,048 NVIDIA V100 GPUs by improving the underlying infrastructure, network, and ML framework. Today, we're open-sourcing the optimized training code for ALBERT (A Lite BERT), a powerful BERT-based language model that achieves state-of-the-art performance on industry benchmarks while training 1.7 times faster and cheaper. This post demonstrates how to train a faster, smaller, higher-quality model called ALBERT on Amazon SageMaker, a fully managed service that makes it easy to build, train, tune, and deploy ML models. Although this isn't a new model, it's the first efficient distributed GPU implementation for TensorFlow 2. You can use AWS training scripts to train ALBERT in Amazon SageMaker on p3dn and g4dn instances for both single-node and distributed training.