The iterations to the review: Your comments should be constructive. Start with things you liked about the draft. Next, suggest concrete improvements. Don’t just criticize. At the proposal stage you should focus on the following

The iterations to the review: Your comments should be constructive. Start with things you liked about the draft. Next, suggest concrete improvements. Don’t just criticize.
At the proposal stage you should focus on the following:
1- Does the dataset seem suitable for the stated problem?
2- Is the goal of the project clearly explained? Focus on the what, not the how.
3- If the how is also discussed, you can comment on that as well. However, this is not the focus of the proposal and any discussion of how should be considered preliminary at this stage.
I need a two-letter of review for each file. it should be less than a page I attached examples as well.
example of the letter
Hi Group,
1- Great project idea and very well proposal wrote by section wise. Here I have a couple of suggestions to improve your project.
According to my opinion, you have not clearly stated the project title and project idea in the proposal. In the project title, you mentioned, “Estimate the performance of machine learning algorithms in forecasting stock prices” while in the deployment section of the project idea, you mentioned, “Present the list of the top ‘X’ best performing stock to the user”. These two things, I personally feel different from each other. It’s better if you will do some modifications to align the project title with the project idea.
Another suggestion is that you mentioned picking 10 company stocks from this dataset. In my opinion, it is a very small dataset to apply ML algorithms. My suggestion is to choose more companies from this dataset to make your dataset large enough for analysis and which will also increase your accuracy in the Regression Model.
I hope my suggestion will help you to improve the project.
2-
It will be a useful tool to protect the interest of both job seekers and the employers. On that purpose, I would recommend my personal suggestions.
1. The data set needs to be defined more explicitly with more details, especially in geographic and cultural dimensions, which is indicative of future applicability and generalizability. For example, if it is a data set of one country or a region, it could not predict the good results with a data of others countries or regions;
2. In the end of the text, instead of “statistical regression”, maybe you want to use logistic regression which is a good model to make binary classification as of your case(fraudulent or non-fraudulent);
3. It is mentioned to implement data cleaning, to use the attributes available and use the (logistic) regression approach. Nonetheless, the whole framework is not clear enough. It is fine we don’t know yet what input variables will be impactful, but we can decide how we can trace and pinpoint them; we also need to what approaches will be employed to optimize the model in an effort to make it effective and easy to be used by the target stakeholders.
I hope that could help!
Order Now

Calculate a fair price for your paper

Such a cheap price for your free time and healthy sleep

1650 words
-
-
Place an order within a couple of minutes.
Get guaranteed assistance and 100% confidentiality.
Total price: $78
WeCreativez WhatsApp Support
Our customer support team is here to answer your questions. Ask us anything!
👋 Hi, how can I help?