Data scientist to build a statistical model

We invite a qualified and experienced data scientist to create a statistical model based on an Excel sheet containing a relational table or database. We would prefer this statistical model built on python. Subsequently, this model will be integrated onto a web-based application. Experience & qualification You should be an expert in Python. Ability to construct a model based on the nearest neighbour algorithm. We will be using this model on a new set of data to ensure that it is working in line with our expectations of accuracy more than 90%. There will be three milestones Milestone - 1 Development of the statistical model. Validation of the model using test data. Milestone - 2 integration of this model onto web application. This is OPTIONAL. Milestone - 3 Real-world validation of models using external data from outside our organisation. OPTIONAL - If you are a full-stack team who is capable of web development too, we will also give this additional task of model integration to you. Front end of this application will be on angularJS JS. You should be an expert in Angular JS and databases such as Mongo DB. Want to know more - here are some more details - here you go! We have basically [disease codes] which are defined by various [features]. There are approximately 45 disease codes and each disease called is defined by a set of criteria or [features]. In an Excel sheet, there are rows which describe the [disease codes] and columns which describe the [features]. If a new dataset comes with a set of [features] then we need to identify how closely it matches with the existing 45 [disease codes]. In other words, by using the model, we would like to know the prediction of [disease codes] from a set of [features] and the accuracy of prediction.