The sprawling Amazon fulfillment center in DuPont, Washington, seems more like the set of a science fiction flick than a warehouse crammed with consumer goods. Thousands of bright orange robots haul heavy stacks of pallets and packages across the slick concrete floor, while hulking yellow robotic arms retrieve and return inventory to sky-high shelves. Yet human workers still roam the DuPont center, fulfilling tasks too complex or granular for the center's fleet of automatons. Around 500 full-time employees help decide which boxes go where and how to arrange products. Unlike the robots, the humans have two key tools -- hands -- for essential warehouse operations like packaging and stowing goods.

It's getting to be a busy time for Brighterion, the fraud prevention engine at the heart of Worldwide and of Worldpay, the largest card acquirer in Europe. The company says there is a "huge business need for inexpensive, adaptable, real-time, cross-channel fraud detection and prevention solutions. However, most existing solutions are built on antiquated technologies such as business rules, neural networks, data mining and statistics. Decision trees are stagnant while fraud schemes continue to evolve." Its relationship with MasterCard began in 2004 when the card company, dissatisfied with its fraud prevention system for detecting too few frauds and creating too many false positives -- denying a purchase to a legitimate customer with a valid credit card -- invited software companies to show what they would do with two years of anonymized MasterCard data.

TaylorMade, an Adidas subsidiary, has three titanium drivers in its 300 Series, the most popular line with professional golfers. But the company doesn't know which $499 club will score best with plain old duffers. To find out, TaylorMade is turning to a fortune-teller: demand management software. Businesses have spent billions in the past few years automating their supply chains. Now many are focusing on the other end of the spectrum: demand.It poses a much tougher challenge and, potentially, a far richer payoff.

Online-only supermarket Ocado is a household name in the UK, and some of you undoubtedly rely on the service to deliver your weekly shop. Something you're unlikely to be aware of, however, is Ocado's work in cutting-edge robotics research. A special division of the company looks at technology that'll ultimately benefit its grocery delivery business. And currently, that arm is involved in developing a robot that would make the most advanced automatons around right now look like Furbies. The SecondHands program aims to build a robot that'll effectively become an Ocado warehouse employee, aiding technicians that work in these mammoth sorting offices with equipment repair and all manner of other tasks.

IN THE old days, knowing your customers was part and parcel of running a business, a natural consequence of living and working in a community. But for today's big firms, it is much more difficult: a big retailer such as Wal-Mart has no chance of knowing every single one of its customers. So the idea of gathering huge amounts of information and analysing it to pick out trends indicative of customers' wants and needs--data mining--has long been trumpeted as a way to return to the intimacy of a small-town general store. But for many years, data mining's claims were greatly exaggerated. Customer-loyalty cards, which allow retailers to gather information not just about what is selling, but who is buying it, sound like a great idea. Yet Safeway, a British retailer, eliminated its customer-loyalty card when it realised it was gathering mountains of data without being able to use it.

Gliding silently through the aisles, it looks more like a moving parking metre than the latest in supermarket technology. But this robot - called Tally - promises to end customers' frustration of finding empty shelves when searching for a particular product. The robot is described as the world's first'autonomous shelf auditing system' and is designed to stalk the aisles looking for stock that is running low. Tally can scan shelves up to 8ft (2.4 metres) high (pictured) to look for gaps, misplaced products and items facing the wrong way, as well as checking prices and checking for out of date products. The machine is also designed to look for price discrepancies or identify stock that is nearing its sell-by-date and so needs to be discounted. Designed by California based start-up Simbe Robotics, the robot is able to capture data on up to 20,000 products in an hour.

I know of no other book on agents...that matches its coprehensive treatment and clear, enjoyable exposition." Van Parunak Centre for Electronic Commerce "Jacques Ferber can legitimately claim to be one of the founders of the discipline that is today known as multi-agent systems. In Multi-Agent Systems, he draws on over a decade of experience as a first-rate researcher and teacher in order to set out a coherent, unified view of the field. The end result is a readable and comprehensive textbook, that will be enthusiastically received by a growing and increasingly important discipline." Mike Wooldridge, Queen Mary and Westfield College "This book is easily the most comprehensive textbook on multi-agent systems and collective intelligence that I have seen.

The shape-shifting robot mannequin, previously only available with a male physique, now comes in female form too. Score one for robot gender equality. The robot is part of a virtual fitting room service for online retailers created by Estonian start-up Fits.me. Customers shopping for clothes at a participating site enter their measurements online (height, chest, arm length, torso, and so on), then see photos of a real-life mannequin shaped just like them (only headless) "trying on" items in various sizes and styles. To be clear, shoppers are not watching the robot try on clothes in real time. When a retailer signs up for the service, Fits.me snaps pictures of the bot trying on the garb in the shop's inventory and stores those photos in an online database that shoppers access later.

Wal-Mart is launching its first iPad app and is refreshing its iPhone app just in time for the holidays. Both applications will enable consumers to shop online or see what's available locally. Orders can be shipped or picked up. The apps are being released ahead of the end-of-the-year shopping frenzy, which many retailers are hoping will be one of the busiest mobile commerce events ever. "As customers use more smartphones and tablets, the Wal-Mart customer is doing the same thing," said Gibu Thomas, the company's SVP of mobile and digital.

A list of transactions from a grocery store is shown in the figure above. Frequent items are a list of items that commonly appear together. One example is {wine, diapers, soy milk}. From the data set we can also find an association rule such as diapers - wine. This means that if someone buys diapers, there is a good chance they will buy wine. With the frequent item sets and association rules retailers have a much better understanding of their customers. Although common examples of association rulea are from the retail industry, it can be applied to a number of other categories, such as web site traffic, medicine, etc. How do we define these so called relationships? Who defines what is interesting? When we are looking for frequent item sets or association rules, we must look two parameters that defines its relevance. The support of an itemset, which is defined as the percentage of the data set which containts this itemset.