As a SMS campaign for example,
(1.) We can use historical data to analysis which customer intend to buy things when we…
(1.) Because data analysis is not the prior part of product if your product is not a data product.
(2.) Can data scientist really know the domain knowledge without being an project holder?
(3.) If there is no data engineer, data scientist can’t do anything. Or you can say that if there is no data, data scientist can’t do anything too.
(4.)data team is a support team in a company, you support the operation in a company, but sometimes you are not nessary.
2. data scientist position in most of the company
How to apply association rules in e-commerce industry ?
1. There are lots of order data in e-commerce, and for marketing colleagues they want to know what combinations of product is the customer’s favorite pattern. So association rule can solve this problem.
2. Product manager wanted to know which product is most buy together by customer, association rule can solve the problem, sometimes you can also use co-occurrence analysis to fix it.
3. Marketing specialists want to know which product categories is most fit to put together on the website.
Automatic model training and testing in GitHub action
(Continuous integration in Machine Learning)
Why we need CI in machine learning?
Machine learning is a very complicate workflow, including data processing, data merging, data modeling, data evaluation, etc.
It takes months to build a useful model, so how can we decrease the time of build model to make different experiment. Automating the process of machine learning is a nice way. CI in machine learning probably can help this, CI in ML make our model more automatic and more easily to check.
This process will make each elements of complicated machine learning…
mongodb altas is like the cloud service of database, before using it you have to make account and setting some things up though.
graduate from applied statistic in Taiwan Good at Machine Learning, Text mining, Deep Learning, Data Analysis....