Thanks a lot NoahNoah Gift wrote:In the example shown there are a couple of "pragmatic" approaches that could tried first, ie. in the spirit of using the highest level tools first. I would approach the problem like this:
Step 1: Spin up an AWS Sagemaker Instance
Step 2: Create a Jupyter Notebook
Step 3: Clean up the data and do some clustering and see if there are some clusters that create types of transactions and plot (with on axis being transaction size)
Step 4: Add the labels to the original data set and predict which cluster something could be assigned to and deploy via Sagemaker (to either production or other team members via about 1 line of code)
Off the top of my head a workflow like this could be a rapid way to approach the problem
Tim Moores wrote:What is or does a "Acquiring Card Payment System"? What does it have to do with reward points?
Tim Moores wrote:What is or does a "Acquiring Card Payment System"? What does it have to do with reward points?
Noah Gift wrote:One particular way to handle things in a pragmatic manner would be to leverage "by the book" recommendations from a Cloud provider: AWS, Azure, GCP. Use their recommended tools and workflows to create a cloud-native architecture that can work with an existing banking architecture. A good example would be to read through some of the AWS whitepapers: https://aws.amazon.com/whitepapers/, then apply that thinking to creating AI solutions for banking.
Tim Moores wrote:What is "core banking"?