This is an exercise in data visualization. It is important to be able to visualize data, to get important insights that may not be apparent when we look at just numbers.
This visualization uses Machine Learning to predict flight delays in departure and arrival and, if possible, utilizing Artificial Intelligence to automate the flight scheduling process of COPA Airlines (which at present is done manually) to increase efficiency, reduce delays, and improve customer experience.
Data of some random flights of Copa Airlines is visualized as a network, where nodes represent the flights, and links or connections between the nodes represent passenger transfers between flights at PTY airport at Panama City. (PTY airport is the hub of COPA Airlines, so almost all flights of COPA Airlines have PTY airport as either origin or destination.)
Nodes (representing flights): All the nodes are in a circular arrangement. Each node is labeled with 6 letters of the flight’s origin-destination code. The first 3 letters denote the flight’s origin airport, and the last 3 letters denote the flight’s destination airport.
* The node color is red for inbound flights (arriving at PTY airport), and green for outbound flights (departing from PTY airport).
* The node size is directly proportional to the flight distance (that is, distance between origin and destination airports).
* Links between nodes (representing passenger transfers at PTY airport, from inbound flights to outbound flights):
* The link color is directly proportional to the number of passengers transferring (varying from light for few passengers, to dark for many passengers).
* Thickness is constant for all links.
Type
DSLR
Artist Affiliation
Graduate Student
Department
Scientific Computing
Area of Research
Data Science / Machine Learning / Artificial Intelligence