I have been working for the last three months as a data scientist for Fresenius Medical Care a german DAX 30 company, which is specialized in dialysis kidney services. Even though I started as a data scientist I am currently in the role of Big Data Solution Architect and jointly responsible for the technical architecture of a central data store.
At the moment the data at Fresenius is isolated in silos. The data produced in the different regions and business units are inaccessible to other parts of the company. To allow for data-driven decision making a centralized store for data…
In performance marketing, an important Key Performance Indicator (KPI) is given by the Click Through Rate (CTR). The CTR is the ratio of users who click on a specific link to the number of total users who view a page, email, or advertisement (ad).
Estimating the CTR is a binary classification problem. When a user views an ad he either clicks
(y=1)or does not click
(y=0). Having solely two possible results let us use logistic regression as our model. Logistic regression is applied to estimate any number of discrete classes in contrary to linear regression, which is used to infer…
Chatbots are coming! They are already taking a market size of 1.17B but grow steeply with a CAGR of 30.9%, which will lead to a market size of more than 10B in 2026¹!
In this guide, we will discover how Chatbot frameworks like Dialogflow or Rasa work. We will build a simplistic model using Tensorflow (TF), deploy the model on the AWS cloud using Serverless and build a React Chat interface to interact with the Chatbot.
Former theoretical physicist and Full Stack Developer who tries to grasp some Data Science.