Abstract is informative, succinct, and clear. It offers specific details about the educational issue, variables (data), context, proposed methods, and measurement of performance/success of the study.
Background
0.5
Use a minimum of 2 or 3 citations Include a general introduction to your topic Narrative integrates critical and logical details from the peer-reviewed theoretical and research literature. Each key research component is grounded to the literature. Attention is given to different perspectives, threats to validity, and opinion vs. evidence.
Problem Statement
0.5
Presents a well-defined and significant research problem Include at least one ML-relevant potential solution. Articulates clear, reasonable research questions given the purpose, design, and methods of the project. All variables and controls have been appropriately defined. Proposals are clearly supported from the research and theoretical literature. All elements are mutually supportive.
Data
1
Multiple data sources for each aspect of the project. All data sources are fully described and referenced. Data is appropriate to the question/goal and large enough data points >1k observations and >5 variable The details of the descriptions also make it clear how they support the needs of the project.
Proposed Solution
1
The elements of the process were described succinctly and with clarity about how they are connected to each other Included description how the solution will be tested.
Metrics
1
The metrics are described clearly and succinctly. Their appropriateness for addressing the research problem is clearly described. Provided the mathematical representations of metrics
Preliminary Results
1
Analyzing the suitability of a dataset or algorithm for prediction/solving your problem Performing feature selection or hand-designing features from the raw data. Describe the features available/created and/or show the code for selection/creation Dataset actually clean and usable after feature selection is carried out Showing the performance of a base model/hyper-parameter setting. Solve the task with one "default" algorithm and characterize the performance level of that base model. At least one of the three: Learning curves or validation curves for a particular model Tables/graphs showing the performance of different models/hyper-parameters
Ethics & Privacy
1
Thoughtful discussion of ethical concerns included. Ethical concerns consider the whole data science process (question asked, data collected, data being used, the bias in data, analysis, post-analysis, etc.). How your group handled bias/ethical concerns clearly described
Team expectations
0.25
The list clearly was the subject of a thoughtful approach and already indicates a well-working team
Timeline
0.25
The timeline was clearly the subject of a thoughtful approach and indicates that the team has a detailed plan that seems appropriate and completable in the allotted time.
Comments
The plots in the visualization part are a bit confusing. To make it easier to interpret the result visually I would suggest making the 'ideal' (the red line) a diagonal line going from the lower-left to the upper-right corner. and making the scale of x and y axis the same for three plots.
And to compare these algorithms you may need to first find the optimal hyper-parameters for each of them (especially forest and boosting?) (just a reminder, ignore this if you are planning to do it)
(sihan)
Project Checkpoint Feedback
Score (out of 7 pts)
Score = 7
Feedback
Rubric
Comments
The plots in the visualization part are a bit confusing. To make it easier to interpret the result visually I would suggest making the 'ideal' (the red line) a diagonal line going from the lower-left to the upper-right corner. and making the scale of x and y axis the same for three plots. And to compare these algorithms you may need to first find the optimal hyper-parameters for each of them (especially forest and boosting?) (just a reminder, ignore this if you are planning to do it) (sihan)