Customer Feedback management is not Market Research …and NPS not the Holy Grail

You’ve probably read hundreds of posts, articles, and books about market research. Over the past several years, another form of asking opinion to customers has also eased into the discussion: Customer Feedback Management (CFM) mainly associated to a specific key performance indicator (KPI): the Net Promoter Score (NPS). Continue reading “Customer Feedback management is not Market Research …and NPS not the Holy Grail”

Text mining using vectors explained to business people

In the last years, a lot of researchers have invested time and resources into a new approach to Natural Language Processing: forget linguistic algorithms, let’s turn the words into mathematical vectors and plot them in a 3D space. Then, applying linear algebra, it allows us to perform specific tasks, such topic detection, sentiment analysis, etc. without even using a single code of pure linguistic algorithms. To nice to be true? Let’s discover the magic word of vectors using a very simple example.

Continue reading “Text mining using vectors explained to business people”

Why can you not explain Net Promoter Score movements over time?

Once again several clients asked me about the reason Net Promoter Score shows high volatility in a trend. The main issue is how to show improvements (or decreases) of NPS and how to assess if the change is statistically significant. (remember, in statistic significant doesn’t mean the finding is important or that it has any decision-making utility, it simply means that you are very sure that the statistic is reliable: not due to chance)

Continue reading “Why can you not explain Net Promoter Score movements over time?”

What are the advantages and disadvantages of using TensorFlow over Scikit-learn for unsupervised learning?

TensorFlow™ is an open source software library for numerical computation using data flow graphs. Nodes in the graph represent mathematical operations, while the graph edges represent the multidimensional data arrays (tensors) communicated between them. The flexible architecture allows you to deploy computation to one or more CPUs or GPUs in a desktop, server, or mobile device with a single API.
Continue reading “What are the advantages and disadvantages of using TensorFlow over Scikit-learn for unsupervised learning?”