DanielHunt27
commented
4 years ago Data Preparation and Modeling (19 out of 20%)
I made sure that all my data was clean, although it was fairly clean when I got it. I think I made accurate models, although I'm sure certain things could be improved.
Validation and Operationalization (19 out of 20%)
I validated both of my models, and did my best to interpret the results. I came up with a way that we could apply what I found from the data. However, I'm sure both of these could be improved.
R Proficiency (20 out of 20%)
I think my R code was good, and I did some more advanced stuff like using an api.
Communication (19 out of 20%)
I tried to communicate everything that I did clearly, although after looking at other people's projects I could have added more comments into my code.
Critical Thinking (20 out of 20%)
I tried to think about how to use the data in a way that would be helpful, and tried to apply my findings in a way that made sense. I also tried to think of what social impacts it could have.
Summary
This project is an analysis and exploration of what predictive factors may increase productivity. Hours worked and amount of compensation appear to be the most adequate indicators of predicting productivity levels. The next planned step is to collect more specific data due to the data possibly being too generalized in this case.
Data Preparation
The tables generated contain information from the US Bureau of labor statistics. There are many variables that are explored regarding compensation, profits, the quarter be investigated, etc. Tables were cleaned and tidied up to represent average hourly earnings, average weekly hours worked, and private employee total. I'm especially impressed with the use of API calls to gather additional data. Great idea!
All tables appear to be very clean and tidy. Excellent work putting this all together.
Modeling
A model was created in order to predict labor productivity utilizing the factors Employment, average weekly hours worked and compensation.
The modelling phase is clear on the steps being taken and articulates findings very well.
The portfolio is accurate in interpreting the model's summary.
Validation
Models were cross-validated successfully using training and testing sets. Accuracy of findings are explained clearly.
R Proficiency
R code is done properly without any iterative approaches. Code is clean and easy to follow. Very well done.
Communication
The writing expresses expert knowledge of the subject matter. Explanations are clear and concise.
Visualizations communicate data adequately. Correlations are clearly shown between various predictive elements. I can't think of any weaknesses from the top of my head. Great work.
Critical Thinking
The discussion regarding operationalization and social impact effectively demonstrates careful, critical thought about the future implications of the project. Other avenues worth exploring are carefully described and demonstrate strong working knowledge of the subject matter.
A possible unintended consequence from the operationalization described (increasing compensation for workers) is the possibility that all basic goods and services could rise if this is done on a grand scale, meaning the increase in compensation could be offset by higher prices for everything else.