Eight Technology Trends Ready For Exploitation In 2018


In the age of disruption, businesses and their leaders will rise or fall based on their ability to spot and creatively respond to rapid technological change. Some companies notice an emerging technology and take a "wait and see" attitude. Others see a new technology and take action. They begin exper...

How four travel brands are using AI for a better experience


Google "the year of artificial intelligence" and the search results definitively bestow that title on 2017. Forbes said so back in February. Google and Microsoft have both declared pivots from mobile-first to "AI-first." An amazing-but-creepy robot has made the talk show circuit. And of course, AI ...

How Chatbots Can Reshape The Travel Industry


Artificial Intelligence has taken the whole world by storm. With so many invaluable endowments of AI, it is hard to extrapolate the immense potential of this state-of-the-art technology. Out of hundreds of applications and use cases of AI, chatbots are creating quite a stir these days. These are bei...

Machine learning drives Grab's Open Traffic initiative


OVER the past few years, the media has focused a lot on how companies the likes of Uber, Grab and Airbnb have exploited the so-called 'sharing economy,' highlighting the fact that they don't own assets but are still able to dominate the transportation and accommodation industries respectively. But ...

Artificial Intelligence: Making Travel Human Again


Artificial Intelligence: Making Travel Human Again. Testing. In this white paper, you'll learn about: The digital transformation in the travel industry; AI and voice recognition for faster booking; Predictive analytics for flight delay notifications; How this technology should be leveraged in 2018 and beyond.

Google Flights will now predict airline delays – before the airlines do


Google is rolling out a few new features to its Google Flights search engine to help travelers tackle some of the more frustrating aspects of air travel – delays and the complexities of the cheaper, Basic Economy fares. With the regard to delays, Google Flights won't just be pulling in information from the airlines directly, however – it will take advantage of its understanding of historical data and its machine learning algorithms to predict delays that haven't yet been flagged by airlines themselves. Explains Google, the combination of data and A.I. technologies means it can predict some delays in advance of any sort of official confirmation. Google says that it won't actually flag these in the app until it's at least 80 percent confident in the prediction, though. (Of course, you should still get to the airport on time, but at least you'll know what you're about to face once there.) It will also provide reasons for the delays, like weather or an aircraft arriving late. You can track the status of your flight by searching for your flight number or the airline and flight route, notes Google. The delay information will then appear in the search results. The other new feature added today aims to help travelers make sense of what Basic Economy fares include and exclude with their ticket price. These low-cost fares are often the only option for travelers on a budget, but they have a number of restrictions that can vary by airline. Google Flights will now display the restrictions associated with these fares – like restrictions on using overhead space or the ability to select a seat, as well as the fare's additional baggage fees. It's initially doing so for American, Delta and United flights worldwide. These changes come only a month after Google Flights added price tracking and deals to Google Flights as well as hotel search features for web searchers. The additions seem especially targeted toward today's travel startups and businesses, like Hopper which had just added hotel search, and uses big data to analyze airline prices and other factors; or TripIt, a competitor of sorts to Google's own travel app Google Trips, which most recently introduced security checkpoint wait times. (Given that Google already knows the busy times for area businesses by tracking people's movement via Google Maps, it wouldn't be surprising to see it implement security wait times next.) The features are also a real-world demo of Google's machine learning and big data capabilities, especially in the case of predicting flight delays. Since you can't take action on the alerts until the airline makes an official announcement, they will largely just cause more anxiety on top of your already stressful travel experience.

Google thinks it can accurately predict your next flight delay


Google is updating its Google Flights feature with machine learning software that hopes to accurately predict if your upcoming flight will be delayed. The company recently revealed the update in a blog post, saying "Using historic flight status data, our machine learning algorithms can predict some delays even when this information isn't available from airlines yet--and delays are only flagged when we're at least 80% confident in the prediction." The post does, however, give the company a little wiggle room for predictions that don't ultimately materialize: Google still advises passengers to arrive on time to the airport. Machine learning algorithms are built to look at a set of rapidly changing data and find patterns. From there, the algorithms make predictions and then learn to make new predictions and decisions. For predicting flight delays, airlines would provide just one piece of that ever-changing dataset. The algorithm would also have to look at other factors, like location and weather, to determine the probability of delays. It could be argued that Google's recommendation that travelers show up on time for their flights regardless of the system's predictions completely refutes the feature's existence. Even so, machine learning algorithms are being deployed in other fields, too -- and with applications that are far from trivial. Researchers from institutions including Carnegie Mellon University and Harvard University have developed a system that accurately identified patients with suicidal ideation. Another system was built by the Computer Science and Artificial Intelligence Laboratory at the Massachusetts Institute of Technology (MIT) that could help doctors more easily identify high-risk breast lesions. For some tasks, the systems have proved so efficient that even employees at the Pentagon are concerned about losing their jobs to AI. It will be interesting to see how these powerful algorithms will continue to enter the mainstream and what effect they might have on the public -- whether they are aware of them or not. Algorithms are a major part of companies' marketing strategies, allowing them to pay for your attention. It may be that the next generation of algorithms will begin to erode the clear lines between our digital and material selves.

Gradient Boosting in TensorFlow vs XGBoost


Tensorflow 1.4 was released a few weeks ago with an implementation of Gradient Boosting, called TensorFlow Boosted Trees (TFBT). Unfortunately, the paper does not have any benchmarks, so I ran some against XGBoost. For many Kaggle-style data mining problems, XGBoost has been the go-to solution since its release in 2016. It's probably as close to an out-of-the-box machine learning algorithm as you can get today, as it gracefully handles un-normalized or missing data, while being accurate and fast to train. The code to reproduce the results in this article is on GitHub.

Google is using AI to predict flight delays before airlines


Few things are worse than waiting an hour to get through TSA for your red-eye, only to realize your flight has been delayed. Google is now using AI to give you a heads-up. Google Flights is rolling out more information on flight delays, including more information on why your departure was actually held back, and even predicting if a delay may happen before you hear anything from your airline. You just need to search your flight number or route and airline to get the information. Google says it's using historic flight data and machine learning to predict delays, and it will only alert you if its more than 80 percent confident in its guess.