The airline industry has been growing at an outstanding rate with an annual growth rate about 6% worldwide in passenger load for the past decade. The airport transport industry around the globe has faced extreme challenges in handling high volumes of passengers due to the economy growth and most of them are already operating at 80% – 90% of their capacity in the last year. The airport functions are very complex with interconnecting decisions and require proper coordination between various functions to facilitate daily operations.
Some of the core functions include passenger servicing, baggage handling, immigration, duty free shopping, leasing of space for retail, and more. All these departments are interested in insights that analytics can provide including information that could potentially assist them in improving operational efficiencies and making their business more sustainable and productive.
Most of the challenges that the aviation industry is facing can be solved by big data analytics. Big data analytics is the complex process of examining large and varied data sets, or big data, to uncover information such as hidden patterns, unknown correlations, market trends and customer preferences that can help organizations make informed business decisions. This enables timely responses to current and future market demands of passengers, improved planning and strategically aligned decision making.
However, analytics by itself represents only part of the solution. It is the combination of data analytics coupled with the predictive prowess of machine learning techniques that truly allow airports to benefit in a variety of ways.
Magellan for Malaysia Airports
Malaysia Airports has begun working with OpenText™ Magellan™ AI Platform for its intelligent automation, predictive analytics, and expanded digital services for passengers at the Kuala Lumpur International Airport (KLIA), including its second terminal KLIA2. OpenText Magellan AI-powered analytics platform was able to model and simulate the information gathered from different data repositories into the data lake and has provided predictive and prescriptive solutions towards problem solving. Learn more in this article and press release.
Magellan for the aviation industry
OpenText Magellan delivers a ready-to-use AI-powered analytics platform, which includes machine learning, data discovery, text analytics and sophisticated visualization and dashboarding. Powered by artificial intelligence & data discovery, Magellan can generate predictive models that allow airports to better plan for and allocate resources where they are needed most, before there is an urgent need to do so, and therefore creating a better customer experience. Through the intelligence gained from advanced analytics, airports can further hone their services based on passenger preferences.
Machine learning and predictive analytics represent the next big wave in airline digitization that uses data, analytics and predictive algorithms. The key lies in the ability to analyze vast quantities of data to provide insights. Magellan BI Reporting does this through advanced visualization in addition with its high availability, reliability and deep security integration. Along with that it also supports everything from a modular, service-based deployment to a full-scale enterprise rollout to millions of users.
Aviation use cases implementation on Magellan
Below are two use cases on Airport Domain with its implementation on Magellan Platform.
- Analyzing Passenger Traffic
- Predicting Flight Delay
Analyzing Passenger Traffic
This analysis is conducted using a public data set that can be obtained here.
Data ingested in Magellan Data Discovery, Magellan Data Discovery enables business analysts to go from raw data to answers in seconds by applying advanced and predictive analytics with a few clicks. Without any coding, business users can apply advanced analytical techniques, such as crosstabs, Venn diagrams, correlation, profiling, bubble charts or maps, to predictive analytics and machine learning techniques, such as anomaly detection, association rules, clustering, decision trees, Naive Bayes classification, linear and logistic regression, and pattern mining—all done via a visual, drag-and-drop interface.
Passenger Data Visualization using Magellan BI & Reporting displaying
- Monthly Trends of Total Passengers
- Passengers by Airlines
- Passengers by Region
- Passengers by Country
Flight Delay Prediction Using Magellan AI
The Magellan data lake is built on top of the Apache Hadoop® platform and Apache Spark™, the powerful open-source platform built for processing big data and machine learning. Magellan leverages Spark components that are pre-integrated and purpose built to deliver a full AI and data science platform. Data scientists can use the Magellan Data Science Notebook with the data lake to create, save and process custom machine learning algorithms using programming languages, such as Scala, Python, SQL and R. These languages are familiar environments that help make it easier for developers and data scientists to get to work.
This analysis is conducted using a public data set that can be obtained here.
Flight Delay Data Visualization using Magellan BI & Reporting
Magellan Notebook: Machine Learning Algorithm has been developed and published using Magellan Notebook
The model is published from Magellan Notebook to Magellan Data Discovery. Magellan Data Discovery is pre-integrated with the Magellan data lake, allowing data scientists to publish models they create, which has the potential to scale their work and make AI more accessible to business users. Once Model is published the business analysts can apply the model with a few clicks or the model can be configured to execute at a scheduled time and stored the results in the Magellan data lake. The accuracy can further be improved by applying other algorithms or tuning the parameters, this blog is mainly focused on demonstrating the Magellan features.
The model is now available for business users to execute from Magellan Data Discovery.
Visit our website to learn more about OpenText Magellan or contact us.
Author: Sridhar Sambarapu, Data Scientist, Professional Services – Center of Excellence
