A helping hand
NavAlgo was created with the mission of helping key players in the logistics industry
to embark swiftly on the AI revolution. The objective was that of assisting clients to
adapt their service offer and their data-driven operations planning to meet the needs
of the logistics market of the future. NavAlgo combines expertise and viewpoints
of active researchers in AI and forecasting, industry practitioners for real-world
logistics operations and experts in business process and pricing design. It works
closely with its clients to design a service which provides the most value to the
end-client, with operations adapting to meet their expectations in an effi cient way.
This means meeting demand where it appears, and providing enhanced supply chain
visibility and predictability.
technology accompanying
shipments and ULDs.
Obtaining the right data
is often linked to the design
and launch of new services.
Introducing door-to-door
shipment services, such
as the ones launched by
Emirates and by Azul, not
only puts airlines in line
with e-commerce providers,
but also provides airlines
with potentially invaluable
datasets, allowing them to
better design and plan their
operations – a factor often
overlooked when evaluating
such premium services from
the perspective of per se
profi tability. In a similar
manner, enabling cargo
tracking technology through
active communication devices
helps collect data which
improves predictability and
forecasts for all shipments,
not only those enabled with
such technology. Guiding IoT
investment, and subsequent
steps such as IoT data
segmentation and analysis,
come as a natural part of the
move towards intelligent
logistics platforms.
The cost of AI
Another point to bear in mind
is that, from a pure business
angle, the costs of deploying
an AI platform do not
depend much on the scale of
operations, while the benefi ts
are incomparably higher on a
larger scale. More pertinently,
in AI methods, performing
global forecasting of demand
and resource planning is
simply much easier to achieve
than local. New forecasting
methods succeed in predicting
the demand for a service
(such as air freight) at a hub
almost perfectly if given
enough data to churn – from multiple hubs, not just the single
hub concerned. In these methods, machines both signifi cantly
exceed human performance, and process more data than a
human operator could ever be reasonably expected to process
or even digest. New machine-based demand forecasting also
proves signifi cantly superior in case of intermittent and irregular
demand patterns, often observed in the case of, for example,
demand for critical shipments.
A note on sharing
All this makes a strong case for what we call “data pooling”
in the cargo industry: multiple actors with similar or even
competing profi les, such as airlines or airports, contribute their
operational data to a third party in a privacy-preserving way,
and take back in return improved forecasts and analytics for
intelligent planning of their own operations. An offering of the
type for the air cargo industry is not yet on the market, and at
NavAlgo, we are actively working towards this aim with logistics
industry leaders. We see such an approach as a way to implement
a vision of intelligent global
logistics with a reasonable
change-management effort,
protecting existing client
relationships and the diversity
of the sector’s ecosystems.
Whether air cargo, post
the AI revolution, manages
to achieve intelligence
without commoditisation
in the New Economy, still
remains to be seen.
NavAlgo is a recent start-up, a contender
in IAG’s Hangar 51 programme, that
majors in planning for supply chain and
formulating logistics based on predictive
analytics. It is also focused on bespoke
AI methods.
www.airlogisticsinternational.com December 2019 43
/www.airlogisticsinternational.com