Review a machine learning small project
- or -
Post a project like this2202
$$$
- Posted:
- Proposals: 8
- Remote
- #1934360
- Awarded
Description
Experience Level: Expert
We are performing a predictive analytics on flights delay using the (Bureau of Transportation Statistics 2017) datasets and related weather data. And during the process we faced some difficulties that led us to question our feature selection, methods and model prediction.
(Project Report,DataSet, and the code files are attached)
Our most important questions are summarized below:
The Data Set:
Is the selected data set good enough to build a predictive model? Do we need to change/add to the selected features?
Is the chosen time series (only 2017) appropriate to build a prediction taking into account the other selected features?
Is (Data Normalization) considered as a necessary step in our case for all features?
And do we always need to transfer the features to dummy variables? If we have to, which features exactly?
How can we fix the imbalance of data? the delay flights are much less.
Used Methods:
Are (Logistic Regression, ANN, KNN, Random forest) considered as the most suitable algorithms in our case?
If not, what other algorithms do you recommend?
How is the (validation set) can be used or applied?
Why is the accuracy low? Can we improve it using the same algorithms? How?
What is the best measure of our model (accuracy, sensitivity)?
How can we compare the different algorithms? How can we write the result in the report? How can we write the conclusion?
(Project Report,DataSet, and the code files are attached)
Our most important questions are summarized below:
The Data Set:
Is the selected data set good enough to build a predictive model? Do we need to change/add to the selected features?
Is the chosen time series (only 2017) appropriate to build a prediction taking into account the other selected features?
Is (Data Normalization) considered as a necessary step in our case for all features?
And do we always need to transfer the features to dummy variables? If we have to, which features exactly?
How can we fix the imbalance of data? the delay flights are much less.
Used Methods:
Are (Logistic Regression, ANN, KNN, Random forest) considered as the most suitable algorithms in our case?
If not, what other algorithms do you recommend?
How is the (validation set) can be used or applied?
Why is the accuracy low? Can we improve it using the same algorithms? How?
What is the best measure of our model (accuracy, sensitivity)?
How can we compare the different algorithms? How can we write the result in the report? How can we write the conclusion?
Hanadi A.
100% (2)Projects Completed
2
Freelancers worked with
2
Projects awarded
50%
Last project
27 Mar 2018
Saudi Arabia
New Proposal
Login to your account and send a proposal now to get this project.
Log inClarification Board Ask a Question
-
Hello. Is this task still available? Thanks
Hanadi A.30 Mar 2018Yes with some updates
-
Hi
Could you let me know more of the project answers share the same data and code with me..
618624609076
We collect cookies to enable the proper functioning and security of our website, and to enhance your experience. By clicking on 'Accept All Cookies', you consent to the use of these cookies. You can change your 'Cookies Settings' at any time. For more information, please read ourCookie Policy
Cookie Settings
Accept All Cookies