← Back to selected work

03 / Cloud data engineering · Machine learning

Bankruptcy Prediction Pipeline.

A cloud workflow connecting data processing, warehousing, and model training for bankruptcy-risk classification.

STATUSCompleted project
KEY FIGURE80% reported processing-time reduction

01 / THE PROBLEM

Context matters.

A useful prediction model depends on the pipeline that prepares its data as well as the model itself.

02 / APPROACH

From idea to workflow.

Built a workflow using Amazon S3, AWS Glue, Amazon Redshift, and SageMaker to connect processing, storage, and model training. Project results reported an 80% reduction in processing time and 97% model accuracy; document the baseline and evaluation method alongside these figures.

03 / TOOLS & METHODS

The stack.

PythonAmazon S3AWS GlueAmazon RedshiftSageMaker

04 / EVIDENCE

Show the work.

Add a real architecture diagram, dashboard screenshot, or model evaluation output here. Explain what the evidence shows and how it was produced.

PROJECT VISUAL

Add a real diagram, chart, screenshot, or model output here.

05 / REFLECTION

What I learned.

Describe one technical decision, one challenge, and one limitation or next step. Specific details make the work easier to assess.

Verify the processing-time baseline and accuracy against the original project. Explain the evaluation setup and data split so the results can be interpreted correctly.