On the fateful Wednesday of November 1st, 2017 Yahoo decided to stop their – until then – free service of delivering real time market data as a text stream through a special URL. For hundreds of businesses and individuals who had relied for years on Yahoo's benevolent free service, this single action meant only one thing: Instant death! Continue reading "Yahoo Finance Live Feeds in Excel after their API Discontinuation in November 2017"
In our previous post on Nelson-Siegel model we have shown some pitfalls of it. In this follow-up we will discuss how to circumvent them and how machine learning and artificial intelligence can[not] help. Continue reading "Pitfalls of Nelson-Siegel Yield Curve Modeling – Part II – what ML and AI can[not] do"
The Nelson-Siegel-[Svensson] Model is a common approach to fit a yield curve. Its popularity might be explained with economic interpretability of its parameters but most likely it is because the European Central Bank uses it. However, what may do for ECB will not necessarily work in all cases: the model parameters are sometimes extremely unstable and fail to converge. Continue reading "Pitfalls of Nelson-Siegel Yield Curve Modeling – Part I"
The Open Source Risk Engine is an opensource software project for risk analytics and xVA. It is written (mostly) in C++ and based on QuantLib. In this post we explain how the ORE can be built from source in Visual Studio 2017. Continue reading "Building Open Source Risk Engine (Quaternion ORE) in VS2017 without Git"
QuantLib Python - a port of C++ library to Python via SWIG - provides a lot of advantages for a practical usage. In particular, it gives a great flexibility due to interactive python console and allows a seamless integration with the AI libraries like Keras and Tensorflow. However, it seems to be challenging to debug the C++ code, called from Python side. So far we found out a quick but dirty solution. Continue reading "QuantLib Python – debugging C++ side with Visual Studio and PyCharm – a dirty way"
It is relatively easy to visualize the aggregated statistics over many periods, e.g. by means of the boxplot series. However, it may be challenging if you want to have a simultaneous look at every element for all time periods. We propose to do it by means of an animated 3D-scatterplot. Continue reading "Visualizing the Fundamental Data on 400 Stocks over 80 Quarters"
We test different kinds of neural network (vanilla feedforward, convolutional-1D and LSTM) to distinguish samples, which are generated from two different time series models. Contrary to a (naive) expectation, conv1D does much better job than the LSTM. Continue reading "Classifying Time Series with Keras in R : A Step-by-Step Example"
Support and resistance levels are quite popular among traders. Although they are implemented in many apps and services, an open source implementation of the algorithm is hardly available. We try to close the gap.
Continue reading "R code to detect support and resistance levels"
I explain how to install QuantLib Python from sources and discuss how to fit a yield curve: PiecewiseLogCubicDiscount and NelsonSiegel.
Continue reading "QuantLib Python – Twisting a Snake to fit a Yieldcurve"
By current artificial intelligence, big data and robo-advisory hype many people believe that computers can do everything for you. I am pretty skeptical about it. Never denying (and actively engaging by myself) a computer-aided trading and investment I always claim "man and machine" rather than "man vs. machine". In this post I show you how to summarize and visualize the data from Alpha Vantage for 6356 American stocks. Continue reading "Visualizing the Data on 6356 American Stocks – with R source code"