Apart from creating model by your own by coding or using Amazon Fraud Detector, you can use low-code/no-code ML services namely Amazon SageMaker Canvas and Amazon SageMaker AutoPilot.
In this demonstration, I will use SageMaker AutoPilot module and calling them via boto SDK. You will need to only specify the target variable (column name), the S3 input and output location.
And then call create_auto_ml_job or create_auto_ml_job_v2 API.
That's it! You have already created the AutoPilot job. After the run, you can get best model candidate and deploy it to the endpoint. Or explore other model candidates created during the AutoPilot job. You can read more details in the notebook solution.
Remark: CreateAutoMLJobV2 can manage tabular problem types identical to those of its previous version CreateAutoMLJob, as well as time-series forecasting, non-tabular problem types such as image or text classification, and text generation (LLMs fine-tuning).