Time series data in the retail world are particularly rich in terms of dimensionality, and these dimensions can be aggregated in groups or hierarchies. Valuable information is nested in these complex structures, which helps to predict the aggregated time series data. From a portfolio of brands under HUUB's monitoring, we selected two to explore their sales behaviour, leveraging the grouping properties of their product structure. Using statistical models, namely SARIMA, to forecast each level of the hierarchy, an optimal combination approach was used to generate more consistent forecasts in the higher levels. Our results show that the proposed methods can indeed capture nested information in the more granular series, helping to improve the forecast accuracy of the aggregated series. The Weighted Least Squares (WLS) method surpasses all other methods proposed in the study, including the Minimum Trace (MinT) reconciliation.

Be it online, offline or omnichannel, today, retail is all about giving the best customer experience and technology is helping the industry to achieve its newly discovered goal. From frontend to backend, the new age technologies like artificial intelligence (AI) are not just making machines smarter but also business by helping it make optimum use of the allocated resources. After a lot of hits and misses, retailers today understand that they have to become a digitally savvy business to remain relevant in the future. If they fail to do so, their stubbornness will make them irrelevant. This awareness and how digitalization will revolutionize the industry is triggering the shift among retailers to adopt new technology. The company has scaled up from a hyperlocal reward program platform to a technology company helping retailers to maximize their marketing campaigns using AI.

An ever-increasing number of retailers are facing up to the fact that Amazon is encroaching on their territory. In recent years, for example, Amazon has spent billions on acquiring Whole Foods, and trialled'checkoutless' retail concepts, as it looks to forge a path into the future of physical retail. Since Amazon's takeover of Whole Foods, the supermarket has been changed considerably to appeal to a broader market. With Amazon continuing to disrupt the status-quo of the retail industry, and now entering the grocery sector, adding this element should be a stark warning to traditional retailers that they need to embrace new technologies to help them win customer loyalty. 'As for the question, did Amazon buy Whole Foods for the groceries or the data?

People attend Shoptalk, a retail and technology conference in Las Vegas. If you weren't at Shoptalk in Las Vegas last week, you missed a great conference. Shoptalk has evolved into a must-attend retail event with more than 8,000 attendees and growing, a destination where retailers and brands go to learn and collaborate and where networking opportunities are key. The conference included content on the latest retail trends around technology, data, and wins and losses in the online vs brick-and-mortar battle. Here are my key takeaways from the conference.

I love shopping at a Nordstrom store, but hate shopping on the Nordstrom website. Unless I know exactly what I want, like my favorite shade of lipstick, I have a time trying to find what I might want. Take a search for a blue dress. Nordstrom served up nearly 3,000 options and after narrowing it down to casual styles, I had a mere 1,000 to go through. Included in that search were jumpsuits (sorry, not a dress), plus sizes and maternity dresses.

Modeling item complementariness and user preferences from purchase data is essential for learning good representations of products and customers, which empowers the modern personalized recommender system for Walmart's e-commerce platform. The intrinsic complementary relationship among products captures the buy-also-buy patterns and provides great sources for recommendations. Product complementary patterns, though often reflected by population purchase behaviors, are not separable from customer-specific bias in purchase data. We propose a unified model with Bayesian network structure that takes account of both factors. In the meantime, we merge the contextual knowledge of both products and customers into their representations. We also use the dual product embeddings to capture the intrinsic properties of complementariness, such as asymmetry. The separating hyperplane theory sheds light on the geometric interpretation of using the additional embedding. We conduct extensive evaluations on our model before final production, and propose a novel ranking criterion based on product and customer embeddings. Our method compares favorably to existing approaches in various offline and online testings, and case studies demonstrate the advantage and usefulness of the dual product embeddings as well as the user embeddings.

Process-Mining techniques aim to use event data about past executions to gain insight into how processes are executed. While these techniques are proven to be very valuable, they are less successful to reach their goal if the process is flexible and, hence, events can potentially occur in any order. Furthermore, information systems can record events at very low level, which do not match the high-level concepts known at business level. Without abstracting sequences of events to high-level concepts, the results of applying process mining (e.g., discovered models) easily become very complex and difficult to interpret, which ultimately means that they are of little use. A large body of research exists on event abstraction but typically a large amount of domain knowledge is required to be fed in, which is often not readily available. Other abstraction techniques are unsupervised, which give lower accuracy. This paper puts forward a technique that requires limited domain knowledge that can be easily provided. Traces are divided in sessions, and each session is abstracted as one single high-level activity execution. The abstraction is based on a combination of automatic clustering and visualization methods. The technique was assessed on two case studies that evidently exhibits a large amount of behavior. The results clearly illustrate the benefits of the abstraction to convey knowledge to stakeholders.

IKEA will reveal the first of its Sonos connected smart speakers at an exhibit in Milan next month. This isn't the first we've seen or heard of the speaker, and we knew IKEA had plans to start selling it in the US and Europe this August. An unveiling next month seems to follow the original timeline, which is good considering IKEA just delayed the launch of its smart blinds. The "bookshelf speaker" is the first in IKEA and Sonos' SYMFONISK range, and a video released by the company suggests we might also see a wall-mounted version in the future. Speakers in the SYMFONISK line will be compatible with Sonos' existing wireless speakers and with IKEA's Home Smart lights and switches, as well as its connected blinds.

At Expedia Group two of our key strategic imperatives are to be customer centric and locally relevant on a global basis. This which is why tools such as Amazon QuickSight are so helpful in making it easier to measure, report, and act on our business metrics to help our customers find the best matches for their travel searches. Amazon QuickSight's out-of-the-box machine learning insights help us to continuously monitor our business for anomalies, alert stakeholders when outliers occur, and help our business project future trends, which in turn allows teams to focus on other priorities instead of building out these capabilities from scratch.

IKEA is delaying the launch of its smart blinds until later in 2019 in order to work on a firmware update. The Verge reports that the Swedish furniture maker pushed back the release date for the smart blinds, which were expected in Europe last month and in the US in April, because it found an opportunity for "improved functionality". IKEA said that the belated launch means that the smart blinds will be compatible with Alexa, Siri, and Google Assistant right away, instead of in a later firmware update. Both the KADRILJ and FYRTUR smart blinds are attractive due to their low price; the KADRILJ starts at around $113 dollars and the FYRTUR starts at around $136 dollars, based on their European pricing. Some existing smart blind options such as Somfy or Velux start at twice that amount.