Data Science Process

This is a Data Science Process I got from Wikipedia. In the real world, we have all the data in the globe. we collect raw data, process and clean up the data to get a clean data. This is the data we can use for exploration. As we collect more data, process and clean and explore again. Another part of the data will be funneled into models and algorithm. The exploring data will go inside and produce data products which are used to generate sales, sometimes coming up with an app itself. I believe Shoppee could have been generated/created from data collection based on shoppers’ purchasing patterns online. which triggered the idea. There are many apps in the market which could be created due to data that they see. In the past, we guess that there is a gap and we fill the gap. But now with more things going into the mobile phones, more data being collected, it will become easier for us to identify the gaps. You need the expertise to identify them. So visualization then you make a decision. This is the whole Data Science Process.