Hi Safegraph team, our objective is to predict the number of daily visits of store, we have built multiple models for multiple brands, We have achieved a mean of 0.8 R2 in the validation data (not seen by the model). In some brands the model performs better (Starbucks 0.92 R2, Walmart 0.94). We are also building a mockup dashboard with the data. You can see all our progress in GitHub - angel-langdon/Project2021: Project from Project III subject from third year of Data Science Degree.
When we have finished our dashboard, could we publish our results in our own webpage (www.entredatos.es) ? If we publish the results the data (data month samples from multiple brands) should be available to download. That is necessary for generating the plots client side.
We would not encourage users to download data, but if they use inspect console from the browser, they would be able to see where the data is coming from and download it.
@Angel_Langdon - this looks awesome! great job on this! just to be clear, you’re trying to show one month of computed daily visits per brand?
@ross_epstein_safegraph yes, something like this, when we have finished the dashboard I will send you the link.
@ross_epstein_safegraph About this :
When we have finished our dashboard, could we publish our results in our own webpage (www.entredatos.es) ? If we publish the results the data (data month samples from multiple brands) should be available to download. That is necessary for generating the plots client side.
We would not encourage users to download data, but if they use inspect console from the browser, they would be able to see where the data is coming from and download it
What is the answer?
@Angel_Langdon sorry we need a bit more information about what you’d be making public. for example, it would be challenging to make available all raw data for every month for every brand. so please let me know when you have more information about what data will be available. thanks!
We would make public samples of data from different brands of Houston and only one month of data maximum
one month of data for each brand
one month == visit count for every day? or a single number of estimated visits for each month?
yes, one month == visits count and much more variables for everyday, I had send you a .json with data sample from a brand