TECH TALK IARTIFICIAL INTELLIGENCE GOES DEEPER NTO AVIATION APPLICATIONS
In this article, I try to cover some of the applications and key areas where this technology is having a signifi cant eff ect. Due to the continuous march of technological evolution, these advances may not have been possible or economically feasible in years past but are so now. Let’s explore what is happening out there.
AIRLINE/OPERATOR REVENUE
MANAGEMENT & OPERATIONS Airlines, charter and business jet operators have been using some early forms of AI for some time relative to revenue management and fl ight operations management, but the combination of today’s AI and data analysis will drive the industry to manage itself better. This can be achieved by how data is gathered more quickly and granularly, which provides AI algorithms with a pool of information by which to make more customized decisions.
REVENUE MANAGEMENT Revenue management is an all- encompassing term that covers such areas as dynamic pricing and price optimization. Many other industries besides aviation do this, such as online retailing (Amazon is a perfect example of how a retailer changes pricing based upon demand, previous customer purchases, time of year and inventory), on-demand transportation
20
DOMmagazine.com | apr 2019
(Uber and Lyft have priced their services based not only on supply and demand but also on scheduled events such as concerts and sporting events in a geographic area which may drive demand spikes for short intervals) and hotels – which have been one of the early pioneers in constantly adjusting their pricing due to demand and oversupply. In the past, the private aviation
industry, in general, has trailed behind many of the more sophisticated commercial airlines in regard to deploying technology to manage its operations and helping customers use its service better. There are many reasons for this, but cost and being able to provide a service built upon automation and intuitive self-learning that fulfi lls every need of a highly- demanding customer segment, the private fl ier, is a diff erent challenge than handling millions of customers. While there is overlap between commercial and private aviation revenue management, one is more concerned with maximizing volume, while the other is more concerned with providing better service to keep its customers. But both are adapting to the way. Internet technologies are driving AI algorithms and machine learning regarding patterns. Dynamic pricing is one area where airlines have been able to even better optimize their base published fares which are already calculated based on fl ight length, particular market
BY JOHN PAWLICKI | OPM RESEARCH
THE AVIATION INDUSTRY HAS MADE USE OF SOME FORM OF ARTIFICIAL INTELLIGENCE (AI) TECHNOLOGY FOR MANY YEARS NOW. ADVANCES IN COMPUTING TECHNOLOGY AND POWER, COMMUNICATIONS AND SENSORING TECHNOLOGY HAVE COMBINED TO BRING ABOUT A NEW GENERATION OF AI IN AVIATION, AND MAJOR INITIATIVES ARE UNDERWAY.
segment characteristics, and broad market segmentation strategies, and then further fi ne-tune these fare prices after gauging data about the inquiring travelers and the market environment. Some version of this technique has been used by airlines for many decades, but now it has moved from a macro level to a micro level where it can change based upon the history of the customer who is seeking to purchase a ticket. The increased use of integrated databases and historical data (e.g., your previous fl ight purchases in years past, seat upgrades, types of seat you prefer: window/aisle/premium-plus/ etc., tour purchases, types of hotels) with other travel service providers support more bundling options and sales of various types of upgrades. The more information an airline/ operator or travel booking website or app has about you (what fl ights you have searched for recently and when, status of your frequent fl yer accounts, hotel points accounts, your browsing history, social media profi les which are linked to you), the better that AI algorithms can fi nd ways to optimize a price and product off erings to appeal to you, and entice you to purchase NOW. Other customers with diff ering needs (or less information available about them, if they did not log in to a site for example) may see diff erent pricing and bundles. Various types of AI and tracking software can use
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68
