ML based project in Python

My goal is to develop a machine learning model to identify network failure patterns. For this project, I will be using supervised learning, and the data provided will consist of both structured and unstructured data. The model will be trained using this data and then will be able to detect and identify any patterns of network failure. This model will be extremely beneficial for detecting potential risks and optimising our network performance. Today’s coherent optical networks are enabled to perform continuous monitoring of the Optical Signal to Noise Ratio (OSNR). Early detection of anomalies in the OSNR can help for proactive network configuration. Through this project we would like to locate a failure in the 4-node ring architecture with the available history of OSNR signatures obtained by the Optical Spectrum Analyzer located at the different nodes. The OSNR samples are collected during the normal and anomaly operation. The project involves in building a Naïve bayes multi-class classifier (with available machine learning libraries) to locate the failure in the lightpaths. The project also involves in the feature extraction and feature engineering from the raw OSNR data.
Programming Language: Python

Skills and experience required:
– Strong knowledge of Python and ML algorithms
– Experience with classification tasks
– Proficiency in using Scikit-learn library
– Ability to preprocess and analyze datasets
– Familiarity with evaluating and optimizing ML models

If you have the necessary skills and experience, please bid on this project and provide examples of similar projects you have worked on in the past.