Each machine learning framework has its own basic data model and it is part of the ‘data preparation’ to convert the existing data to the required input format of the specific framework. Most of these frameworks also provide a direct access to some predefined data-sets (e.g iris, mnist etc) I Read more…
Forecasting The longer you look back, the farther you can look forward. (Winston Churchill) Forecastig of the development of stocks is quite a challangning task with uncertain outcome. We currently support the following approaches: – Forecast based on History – Arima Setup %classpath config resolver maven-public http://pschatzmann.ch:8081/repository/maven-public/ %classpath add mvn Read more…
Edgar can be used to analyse the financials of a single company over time. However, we try to get an overall picture of the profits over all companies. For this we use the Python Data Analysis Library Pandas and my simple Edgar REST API. In [199]: import pandas import matplotlib.pyplot as Read more…
I was curious about the usefulness of the Edgar Database: Is is possible to predict the development of the stock price using the company filings? Can we predict the total yearly profits for the current year based on the filings of the current months? Is the overall profitability changing over Read more…
Today, I was putting together and testing my Data Science Toolbox in Docker which consists of the following components: GUI/Environment – jupyter – python3 Core Libraries – NumPy – SciPy – Pandas Visualization – Matplotlib – Seaborn Machine Learning – SciKit-Learn – Keras – TensorFlow It is based on the lean Read more…