Using airport and airline data from the DOT we aimed to create a dashboard that would showcase several different optimizations and weather details. The first optimization was a simple historical analysis to identify a trend in delays between origin destination pairs during certain months. The analyzed data allows for the average delay between airports to be identified for each month. This can be useful when making travel plans, i.e. whether to fly out of Bradley or JFK, as well as for airports/airlines to identify which flight routes cause the most delays. The second optimization joined datasets for geographical coordinates, average price of airline tickets per airport, and delays. The goal of this optimization was to create a graphic that allowed a user to compare the cost of a flight and the likelihood of a delay. Next the Random Forest Algorithm was evaluated more closely to create a more accurate prediction for delays using weather and the flight itself. Random forest was chosen because it can deal with both continuous and categorical data which fits with our dataset. Our project made use of Dataiku, a powerful AI and machine learning tool which allowed us to create and deliver advanced data analytics. Using Dataiku we were able to clean data, join different datasets, stack data, create charts and models, and run a variety of different algorithms. Apache SuperSet was used for our dashboard development. Apache Superset allowed us to easily add datasets from dataiku to create graphics which allowed us to further analyze/visualize trends as well as key details in our data. It also allowed us to effectively display the models we used on the datasets. The above services share data through a shared PostgreSQL server and are all deployed on Kubernetes for ease of deployment and maintenance.