Predictive analytics 'can boost airlines' ops, profitability'

AIRLINES can leverage on predictive analytics to make better operational decisions and run more profitably as they navigate a tough operating environment, according to software firm FICO.

There is rising interest from airlines as carriers seek to protect already thin margins amid challenges such as volatile fuel prices and currency exchange rates as well as aggressively expanding budget carriers, noted Amit Parekh, director (Asia Pacific) for NYSE-listed FICO.

The International Air Transport Association recently revised its 2014 industry outlook downwards slightly, projecting an industry profit of US$18.7 billion versus US$19.7 billion previously on the back of higher oil prices. Revenues are expected to hit US$745 billion, translating to a net profit margin of just 2.5 per cent.

Optimisation of pairing and rostering under crew scheduling - which for instance can minimise allowances and expenses to keep operating costs in check - can save an airline millions of dollars annually, says Mr Parekh. The immediate impact from more optimal crew scheduling is 10-20 per cent savings on variable costs, he added.

In terms of rostering, suitable crew can be matched to routes based on their qualifications, fatigue profile, availability and skills, such as language capabilities.

Other areas that carriers can use predictive analytics to run more efficiently include fleet planning and scheduling; maintenance, repair and overhaul; capacity planning, flight planning as well as price optimisation.

"Sometimes the difference between a flight being profitable or losing money comes down to just a couple of unsold seats," said Guitao Yu, deputy manager of the Information Centre at China Southern Airlines.

Pricing a ticket accurately will result in better yield and revenue management since an unsold ticket is revenue lost. FICO, which counts carriers such as China Southern and Malaysia Airlines among its customers, highlighted that improvements to its Xpress Optimization Suite software over the years has also made the programme quicker and more efficient.

"The Xpress optimisation performance on our airline test set has improved by 300-400 per cent in the last 10 years," Mr Parekh added. "If you factor in the increased hardware speed this means that for a medium-sized airline, a typical crew planning optimisation run takes only 2-3 minutes compared to an hour a decade ago."

Analytics can also be applied to other industries, such as banking, insurance, retail and manufacturing.