Scribd
Upload
6 views1 page

Data Science ML Engineer Task Overview

The task involves preprocessing a dataset to clean external status descriptions and internal status labels for machine learning. A model will be developed using TensorFlow to predict internal status from external descriptions, followed by training and evaluation using metrics like accuracy, precision, and recall. An API will be implemented with FastAPI to expose the model, and thorough testing and documentation of the entire process are required, with a public GitHub repository for submission and an optional deployed API URL for bonus points.

Uploaded by

Ajay Kumar
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
6 views1 page

Data Science ML Engineer Task Overview

The task involves preprocessing a dataset to clean external status descriptions and internal status labels for machine learning. A model will be developed using TensorFlow to predict internal status from external descriptions, followed by training and evaluation using metrics like accuracy, precision, and recall. An API will be implemented with FastAPI to expose the model, and thorough testing and documentation of the entire process are required, with a public GitHub repository for submission and an optional deployed API URL for bonus points.

Uploaded by

Ajay Kumar
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Settyl Data Science And Machine Learning Engineer Task

Task -

Dataset:
[Link]

Data Preprocessing: Preprocess the provided dataset to clean and format the
external status descriptions and internal status labels for training the machine
learning model.
Model Development: Develop a machine learning model using TensorFlow or
similar frameworks to predict the internal status based on the external status
descriptions. Experiment with different architectures and algorithms to achieve
optimal performance.
Model Training and Evaluation: Train the developed model on the preprocessed
dataset and evaluate its performance using appropriate metrics such as accuracy,
precision, and recall.
API Development: Implement an API using FastAPI framework to expose the
trained machine learning model. The API should accept external status descriptions
as input and return the predicted internal status labels.
Testing and Validation: Test the developed API thoroughly to ensure its
functionality and accuracy. Validate the predictions against a validation dataset to
measure the model's generalization ability.
Documentation: Document the entire development process, including data
preprocessing steps, model architecture, training procedure, API implementation,
and testing results.

Submission:
- Public Github Repo

Bonus:
- Deployed API URL

You might also like