Machine Learning
Budget: $10 – $30 USD
JOB: Develop Machine Learning Models for Predicting Atmospheric Emissions
I need your help in developing machine learning-based models for predicting atmospheric emissions (and pollution) from data gathered by various borough and county environment monitoring units from the dataset of the URL below.
https://data.london.gov.uk/dataset/london-atmospheric-emissions-inventory-2013
The web page describes the various types of data held for monitored atmospheric emissions for the year 2013 but only focus on 2013.
Tasks
1. Identify and describe in some detail at least 3 machine learning algorithms/techniques that you intend to use in this project. Provide your reasons for selecting those ML methods.
2. Specify the types of predictive insights you expect to glean from the data after you have applied your ML models. Your response should be based on an actual inspection of the datasets and should be as specific as possible.
3. Develop the respective ML models using your Jupyter notebook and Anaconda/Scikit-Learn toolkit to work on the datasets available on the website.
4. Assess the performance of each model using suitable ML metrics and explain in detail any differences in model performance.
5. Summarizes in a writing the work carried out for tasks 1 – 4, and which presents salient ML modelling results obtained.
I need your help in developing machine learning-based models for predicting atmospheric emissions (and pollution) from data gathered by various borough and county environment monitoring units from the dataset of the URL below.
https://data.london.gov.uk/dataset/london-atmospheric-emissions-inventory-2013
The web page describes the various types of data held for monitored atmospheric emissions for the year 2013 but only focus on 2013.
Tasks
1. Identify and describe in some detail at least 3 machine learning algorithms/techniques that you intend to use in this project. Provide your reasons for selecting those ML methods.
2. Specify the types of predictive insights you expect to glean from the data after you have applied your ML models. Your response should be based on an actual inspection of the datasets and should be as specific as possible.
3. Develop the respective ML models using your Jupyter notebook and Anaconda/Scikit-Learn toolkit to work on the datasets available on the website.
4. Assess the performance of each model using suitable ML metrics and explain in detail any differences in model performance.
5. Summarizes in a writing the work carried out for tasks 1 – 4, and which presents salient ML modelling results obtained.