Airports, airlines and other travel-industry sectors have to solve complex business challenges such as determining total market size at the flight coupon level, predicting customer behavior, cabin class mapping and trip classifications. Data trends and historical data collected before the COVID-19 pandemic are no longer reliable to meet the current demands of the industry; data needs to be thorough, timely and provide market competitiveness.

ARC has innovated how travel-related businesses can make informed decisions by applying machine learning techniques and technology with Advanced Data Analytics.

Best-in-Class Product Development

ARC’s Director of Product Management and Data Products, Shitalkumar (Shital) Sabne, is a data analytics trailblazer and leads his team to find solutions for industry stakeholders to maximize their business potential. He is especially enthusiastic about Advanced Data Analytics, “ARC has been devoted to answering the burning questions many travel industry customers have: Is this trip a business or a leisure trip? What is the fair market share of an airline? How do we best predict scheduled itineraries?”

“We believe we finally have the answers! Our product team has used our extensive industry experience and artificial intelligence (AI) to develop advanced analytics and capabilities for our customers. We look forward to seeing this suite of data solutions transform their businesses.”

Data Powered by Artificial Intelligence

ARC leverages Amazon's SageMaker technology to provide next-generation data for total air market estimates, airline cabin class mapping, quality service indexing and trip classifications. This information will give reliable tools for relevant and accurate business decisions.

Total Air Market Estimates

ARC’s Total Air Market (TAM) provides estimated datasets that enable customers to understand total global air market size, carrier market shares, traffic distribution, demand growth and fare patterns. Total market size at the flight coupon level is provided with actual tickets and estimates of extra traffic.

Sales, refunds and exchange information are refreshed weekly for minimal lag time. Users can see estimates of total traffic statistics from nearly 2000 airports and load factors from more than 400 airlines. The program has strict quality control measures and is recalibrated regularly.

Quality of Service Index

ARC Quality of Service Index (QSI) combines travel attributes to calculate expected QSI share: service frequency, number of stops, aircraft type and capacity, and additional essential trip details. With this data, airlines can predict customer behavior by quantifying the relative attractiveness of flight options by market (O&D City pair) from published airline schedules.

Cabin Class Mapping

The certainty and breadth of cabin mapping data have been lacking until now. ARC’s Cabin Class Mapping (CCM) offers users the most accurate and timely cabin mapping information based on carriers, routes and fare types.

CCM uses machine learning to group Reservation Booking Designators (RBKD) into a cluster and map cabin classes. This technology is more advanced than any legacy industry standard.

Trip Classification Indicator

The travel industry now has a reliable way to differentiate trip purpose for each airline ticket. ARC has built a Trip Class Indicator (TCI) model utilizing machine learning algorithms. The TCI algorithm starts with capturing key attributes for each ticket and is then analyzed against the ARC database. Combined with Amazon SageMaker Services, these steps capture detailed insights into passenger behavior.

The advanced segmentation data delivers comprehensive trip attributes to determine if a trip is for business or pleasure. The program is designed to continuously be recalibrated to capture ever-changing passenger behavior.

A Better Way to Make Business Decisions

Let’s put Advanced Data Analytics to work for your business. With ARC’s AI, you will enhance your strategic planning and operational management in specific markets. Contact us today to get started.