Peer review - Group A

[LeNguyenNhatMinh]

Overall, your team's project has shown great potential for social impact by increasing awareness and understanding of gender pay disparities. Strategic improvements in data handling and feature innovation could elevate its effectiveness and uniqueness.

Suggestions for Improvement:

Novelty and Differentiation

Issue: Gender pay gap visualizations are relatively common. Numerous organizations and media outlets have produced various interactive tools to explore these disparities.

Suggestion: To differentiate this project, consider incorporating predictive analytics to forecast future trends based on historical data. Additionally, integrating external factors such as economic changes or legislative impacts could provide a more comprehensive analysis of why gaps exist and how they might evolve.

Clarity and Additional Features

Unclear Aspect: It’s not entirely clear how the dashboard will handle the visualization of complex multi-dimensional data in a way that remains user-friendly and not overwhelming.

Suggestion: Implement features like dynamic filtering, where users can select multiple sectors or adjust date ranges to compare data side-by-side. Providing guided tours or tooltips that explain the data and visualizations can enhance user understanding.

Questions:

How will the project address potential anomalies or inconsistencies in the data, especially considering the long time span from 2017 to 2023? What methods will be used to ensure the reliability of the analyses performed?

Given the potentially large volume of data and the complexity of the interactive elements, how will the dashboard ensure good performance and scalability? Are there any specific technologies or techniques being considered to manage these aspects?

[khaukhau]

• Suggestion: Regarding incorporating predictive analytics to forecast future trends, we will implement this suggestion to predict the pay gap in various sectors and years.
• Clarity of data: We do not have complex multi-dimensional data as most of our data is just 2D.
• Question 1: To address potential anomalies or inconsistencies in the data spanning from 2017 to 2023, our project will employ a multi-faceted approach. Firstly, we will conduct through data validation and cleaning process. We will only use companies that submitted sufficient data. Secondly, we will implement robust outlier detection techniques to identify data points that deviate significantly from expected patterns.
• Question 2: To ensure good performance, we will employ modern front-end frameworks to optimize for rendering complex visualizations with minimal computational overhead.

[tienvu95]

I think for project 2, it's important to do sth new (as compared to project 1), so adding predictive feature is important.

Additionally, once we implement predictive technique, we should thoroughly examine the logic/ robustness of our method. If our method is not solid --> our important feature might not be usable/ reliable

Last point mentioned is also important, we should ensure that our dashboard loads smoothly everytime we fetch/ filter. Given that we are incorporating predictive technique, we should ensure that we have minimal computational overhead

Note that you don't have to reply to this comment, this is just my thought on what you can do to improve your project.