AVIAPRO CONSULTING BLOG

 

Data Analytics; Transforming the Aviation Industry

21 December 2023

A Q&A with AviaPro partner, Datahub Consulting’s CEO, Clive Lemmon, delves deeper into the realm of data analytics and its powerful impact on airlines operations. Underestimating data analytics can lead to missed opportunities and even the risk of being left out from the competitive scene.

Airlines compete on a limited number of passengers thus making analytics a crucial parameter in their success to grab the largest market share with the most profitable scenarios.

Ali Kassir, Airline System IT Specialist at AviaPro Consulting, had a chat with Clive Lemmon about business intelligence, challenges with data collection and analysis, interpretation of data, security compliance, upcoming trends and more.

Q&A

1. Can you provide an overview of how data analytics is transforming the aviation industry? What role do AviaPro and Datahub Consulting as partners play in this transformation?

For me analytics is the reports and dashboards that users see and use. It turns data into information, insights, and trends. Any person trying to analyze the data themselves would find it impossible to interpret billions of rows of data into meaningful information or trends. But with analytics this is possible.

So how would we apply this to aviation?

As a consulting organization that works with many airlines and airports across the world, there are many use cases where airlines are reliant on Excel sheets and manual reports to interpret the data. Datahub have engaged with these airlines to look at the processes used within the airline, create an analytics roadmap, then integrated Microsoft power BI to create insights. 

Why is this the case?

Airlines like other industries want insights anytime, anywhere, and on any device. Data is increasing exponentially, and airlines are wanting to use it to their advantage. This is getting too much for analysts to use Excel sheets or database queries to provide the management with near real time insights. This is where analytics applications are key. With modern technology it’s possible to get sales trends based on yesterday’s data anywhere using the cloud, and on any device from laptops, tablets, and mobile phones.

 AviaPro, as an airline consulting provider, is able to enhance its offering to its clients by partnering with DataHub. Transforming how the aviation industry process the data that is crucial to their operations in an efficient and reliable manner

 

2. How do Analytics and Business Intelligence help aviation companies make informed decisions?

Firstly, what is the difference between Business Intelligence and Analytics?

For me, analytics is a subset of business intelligence, where business intelligence is the collective name for an end-to-end process. Business intelligence includes the data warehouse where the data is held, cleansed, and moved into the data warehouse using an automated process called ETL (Extract, Transform, and Load), adding business logic like specific calculations relating to the industry, and then presenting the data using an analytics tool such as Power BI, Tableau, or Qlik.

Business Intelligence

Allows airlines and airports to collect historic data in one large database called a data warehouse to allow for quick analysis of data. A data warehouse can get data from numerous sources and combine it into one centralized model. With data from numerous sources, it provides even more meaningful information.

An example of this would be the reservation system. Most airlines use a third-party reservation system that collects the transactional data for each reservation. Having an automated feed from this reservation system into their own data warehouse allows the airline to look at changing trends over time and analyze the historic data. Some key year-on-year comparisons, month-to-date sales revenue, or seat utilization etc. This could be possible using the third part reservation system but having a data warehouse is a better, more flexible solution that is built around the specific airline.

Analytics 

Here are some of the questions that analytics can answer:

Trend analysis of ticket sales

• What is the number of weeks prior to the flight that sales of business class peak. Comparing one route to another?
• What is the average age of passengers using first class on each route.
• How many passengers are part of the frequent flyer program (FFP), comparing the last 5 years.
• How many passengers use the lounge facilities at each departing airport?
• Analyze meal preference: On a particular route what are the meal preferences. Does the London to Dubai flight require more vegetarian meals than the Paris to Dubai flight? Having the right number of meal preferences for the passengers is part of the customer satisfaction journey.

 

3. Data compliance is a critical concern in data analytics. How do AviaPro and Datahub Consulting ensure data compliance in the aviation sector, which often deals with sensitive information?

With the increase in cyber security attacks and new data protection laws regulating the use of personal information. Having governance alongside your analytics is key and essential. This is why working with a consultancy that has data engineers and data scientists working alongside data protection professionals is paramount.

General Guidance

• Only include the personal information in the database that’s required (data protection minimization principle). For example, if there’s a financial reporting system the passport number, nationality, or date of birth may not be required.
• In the reports and dashboards, not to allow personal information to be visible unless it’s essential. Most reports and dashboards require aggregated data and personal information is not required. What I mean by “aggregated” is numbers, counted, summed, or forming an average. For example, 
  • What is the seat utilization as a percentage for flight A compared to flight B.
  • What was the total number of children travelling on the AM flights compared to the PM flights. We don’t need to know the children’s names or any other personal information just the count of children.
• When reporting by age, remove the date of birth as this is considered personal information. Instead create a column in the reporting data that has the age of the passenger. From a data protection point of view the age of the passenger would not be considered as personal information compared to the date of birth. It would be better to include in the reporting data that the passenger is 56 rather than using the date of birth in the form of mm/dd/yyyy.  The age could be calculated using the date of birth in the data warehouse. But only make available the age or age band in the reporting data.
• When there’s a need to include personal information, include the appropriate security measures to protect the data. This can be achieved with techniques such as row level security. Row level security ensures that individual users can only see the data they need to. The security uses the email address to identify and filter the data based on what they have access to.
• To comply with ISO 27001 and data protection, sensitivity levels are required. Sensitivity levels allow an organization to categorize the content of the data with a label. Typically, these labels are confidential, private, public etc. Analytics tools like Azure services and Microsoft Power BI have sensitivity levels built in to the applications, allowing organizations to use these as part of a security strategy.
  Learn about sensitivity labels | Microsoft Learn
• As a partner of Microsoft, with the new Microsoft Fabric analytics, data engineering, machine learning, data governance, and data compliance are all together under one platform. This allows Microsoft fabric to integrate compliance to data protection easily. 

 

4. What specific challenges do aviation companies face when it comes to data analytics? Are consulting companies up to these challenges?

Volume of Data

One of the biggest challenges is the volume of data. Airlines have access to vast amounts of data. To have a competitive advantage over other airlines then they need to make sure they maximize the use of this data. This is a challenge, as they may not understand how to use it to maximize efficiency and customer satisfaction etc. This is where a data consultancy can work with the airline to overcome this challenge.

Personalized Customer Experience

One of the biggest growth areas in aviation data is personalizing the customer experience. Passengers not only want airlines to take them from one destination to another. Customers want to have a personalized service included. This includes airlines collecting preference data, being able to interpret this, and personalize it to the customer. Does a passenger like a window seat, do they need any support, tailormade offers sent to their devices, do they travel for business or family vacations, do they have any dietary requirements etc.?

This requires a data driven culture from the airline. It includes building a profile of the customer using business intelligence and machine learning. This personalized experience has been used in retail (like Amazon) very successfully. Now airlines need to provide these services.

Changing Technology

Cloud technology is evolving year on year. Airlines have specialist IT people and analysts but with business intelligence and machine learning then there’s a need for subject matter experts to help. With data and cloud technology airlines want to invest in the future. Have a custom-built end-to-end solution that is robust and future proof. 

For example, with technology today there are dedicated and serverless cloud database systems, each with their own pros and cons. Knowing what technology will be right for the airline’s needs is a challenge. Having a specialist that can understand aviation data and the requirements of the airline, create a roadmap that can deliver, design, architect and develop an efficient cost-effective solution is key.

Integrating Affiliated Companies

Many airlines that I’ve worked with have affiliated companies that could include airport services, catering companies, aircraft maintenance companies etc. Integrating the data from affiliated companies into the airline, so data is accessible across the group is a challenge. We have addressed this challenge many times by utilizing cloud technology.

 

5. With the rapid growth of machine learning and automation, how are these technologies expected to benefit aviation clients?

Aviation is one of the fastest growing industries adopting machine learning and automation. 

Why is this?

Let’s have a look at some examples that airlines are adopting.

Flight Delays

Within machine learning there are several examples available for predicting flight delays. Flight delays lead to a negative impact on the airline. These algorithms predict the likelihood of a flight being delayed taking several factors into consideration, including weather, route, outbound and inbound airports. The algorithm is trained on historical flight delay information from the airline, FAA, historical and forecasted weather, and the current state of the national airspace system.

Ticket Pricing

Have you looked at a flight and seen the price go up and down. 

Pricing strategy is a complex subject and to explain it in detail would require an article by itself. But availability and demand are two factors that are used within the pricing of seats. Allowing a machine learning algorithm to set the price of tickets is key to optimizing ticket pricing strategy.   

Seat Utilization

It’s well documented that airlines oversell the seats as they know that some passengers will not check-in and the seat will be empty. So, airlines will sell more seats than is available, reducing the number of empty seats on a flight. But this is a risky decision. How many passengers that don’t check-in will only be confirmed about 90 minutes before the flight departs. Machine learning can help with this.

Machine learning can look at the patterns for a particular route, on a particular day and time, together with other factors and accurately estimate the number of passengers that are likely to not check-in.

Predictive Maintenance

An airline is only making money when an aircraft is in the air. The more time that the aircraft is on the ground, the airline is potentially losing revenue. In some cases, it will cost them money.

Predictive maintenance is looking at the individual parts on an aircraft and proactively carrying out maintenance so that failures on an aircraft are kept to a minimum. When a part or system on an aircraft fails it’s then grounded until the problem is fixed. This can cause delays, cancellations, airlines may have to pay additional fees to passengers and airports, and customer satisfaction is then reduced. I’ve personally travelled with a particular airline 7 times. Out of those 7 occasions the plane was delayed 5 times. 3 of those times were due to a problem with the aircraft.

Machine learning can look at an individual aircraft and use the data to predict the potential failure point of a part or component. Knowing this information, the airline can then plan for the part to be inspected or replaced. With planned maintenance this does not cause the airline any disruption and can minimize the cost impact.

Customer Preferences / Segmentation

Airlines, like hotels, want to provide not only a service but also a personalised experience. Travel isn’t just getting from one country to another, it’s making the little details matter that makes the customer want to travel with the airline. 

To provide a personalised customer experience, organisations are putting the customer at the centre of their business. So, from an airline perspective how can they use machine learning to achieve this? 

Firstly, by collecting data on customers listed below the airline can get a better understanding of their customers, their needs, preferences, and how the airline can personalise the customer experience.

Examples of datasets required to personalise customer experience: 

• Customer behaviours
• Reservation history
• Google analytics 
• Historic purchase history

Once that a profile (or a picture) has been created of the customer then the machine learning model can then make recommendations to the customer. Amazon use this type of machine learning a lot. This type of machine learning is called a Recommendation Engine. 

Optimizing fuel Consumption

All airlines are looking to save money but also to maximise the service to the customers. There are different ways to save money and one is to reduce the fuel used on a flight. Pilots can do this to an extent with their speed and altitude, but weather also plays a big part in this. For example, if a plane is flying into a headwind, then it will need more power (thrust) to maintain a particular speed than if it had a tail wind. So how can machine learning look at optimising the fuel consumption. Qantas are the first airline to have flown a scheduled flight between Australia and London (LHR), a 17-hour trip nonstop. It’s also not surprising that Qantas are also using machine learning within their flight operations. 

Let’s look at an example of how using weather could help reduce fuel consumption, also reducing carbon emissions. Within the flight operations team at an airline, they plan the flight details of a scheduled flight. This could include the time of the flight, the aircraft used, and routing etc. Now if they included weather data and machine learning into the decision making, they can reduce fuel consumption. For example, if a machine learning algorithm has weather data that included wind direction, wind speed, any bad weather like storms, then this could play a considerable role. So, if the algorithm recommended that a plane fly’s 5 degrees east of its planned route and would then get the benefit of a tail wind this could reduce the fuel consumption. 

If you find machine learning interesting, then please have a look at this article that I’ve created. Machine Learning in Aviation | DataHub Consulting 

 

6. How does data analytics contribute to safety and efficiency in the aviation industry, and what are the potential future developments in this area?

One of the key areas where analytics can contribute to safety is within airports. 

Incident Management 

• Health & safety incident reporting
  With the high volume of people using airports daily there will be regular health and safety incidents. This can be analyzed and managed efficiently. For example, how many incidents required a paramedic to attend, and how long did it take to respond. How many incidents caused flight delays and how can this be reduced.
• Analysis of root cause of incidents
  With any incident, especially at airports, the management team would want to know root causes and ways to reduce the incidents. This again can be achieved with analytics.

Regulatory Compliance

Also, analytics can assist airports in ensuring compliance with safety regulations by tracking and analyzing safety metrics.

Staff Utilization

Using data analytics, management can analyze trends to identify where staff should be utilized to minimize queues and to speed up movement through the airport. Understand bottlenecks in the airport process and compare the performance of the airport against other airports.

Staff Training

One area that Datahub has used analytics in an airport is with staff training. There are a lot of staff in the airport from security to fire crew. For a lot of these there is regular training and assessments that need to be addressed. Having an analytics solution with automation, managers can get reports on staff that are due to have training or assessments in the next 120 days. This means that managers get early warning and can effectively plan for this. The automation can email staff or the managers of up-and-coming training or assessments.

There are many more examples, but this gives an idea of how effective analytics can be within a busy airport.

 

7. Digital transformation is a buzzword in many industries. How do you think support should be given to aviation companies in their digital transformation efforts, and what are the key aspects of this transformation?

Like any industry digital transformation is what most organizations are looking at. Reducing paper-based tasks, reducing manual effort, reducing errors, working more efficiently. Let’s look at some examples.

Customer Feeback

Digital transformation can be used for customer feedback surveys to understand how the airline or airport performed. But also, if any negative feedback was submitted digital automation can alert the customer service team along with the manager responsible for the area with the negative feedback.

Having this digital automation in place saves time for a person to manually look through all the feedback to understand the negative areas.

Optimizing Workflows

As airlines and airports are 24/7 operations optimizing any workflow can improve efficiencies. This could be alerting staff to delays. Another example would be with the CCTV monitoring of vehicles or people. With people, CCTV images could be used with digital transformation tools to understand and optimize footfall in particular parts of an airport.

With digital transformation tools, cars dropping off passengers at the airport could be analyzed and alerts sent to staff or departments based on congestion. 

Challenges to Consider

Automating more and more processes and in turn reducing some of the manual interaction can have its challenges. One example is, if personal information is involved, then data protection law means that a risk assessment would need to be carried out. With many of the data protection laws, EU GDPR is one for example, requires a DPIA to be completed where a new process has been implemented, or a process have been changed significantly. Automating a process that involves personal information could be considered a significant change.

 

8. Can you highlight some upcoming trends or innovations in data analytics that are particularly relevant to the aviation sector?

Future Travel Experience 

Guest experience and technology, with passenger numbers increasing in the millennials bracket (people born after 2000) then this is predicted to change the approach of airlines and airports. Digital first experience is becoming essential. For example, when a passenger enters an airport, especially an overseas airport that the passenger is unfamiliar with. Passengers are starting to use interactive maps on large screens, or interactive services on mobile technology to get them through the airport. 

Passenger Demand

2024 is predictive to see increase in passengers compared to 2022 and 2023. This is due to the industry recovering from COVID and then a global recession. Understanding demand can support airports with strategic planning for recruitment of staff.

Climate

In the next few years weather and climate related delays are estimated to account for 64% of total delays. With climate change countries around the world are seeing more storms, high winds (more than 60mph), this is impacting scheduled flights causing delays and cancellations. Being able to analyze and understand this impact allows for airlines and airport to strategically plan.

How Does Climate Change Affect Destinations

The change in climate is predicted to affect destinations as passengers are expected not travel to destinations with extreme heat. Destinations previously visited are expected to decline and passengers could opt for destinations that are a bit cooler. Analyzing trends on passenger numbers by month of year and the climate can give insights into change of destination preferences.

 

Clive Lemmon
CEO of Datahub Consulting
Data Consultancy Services | Datahub Consulting

Read more on the AviaPro Blog