## LSTM, 1 property, 1 stock on normalized data

This code is the result of some work I have done on LSTM. Purpose: predict the next day price with the use of a LSTM neural network and just one property. How: I have normalized the data, I have used just 1 parameter as input (close price), I have built the code using basic functions … Read more

## Year 5, Q1 Wardley Maps + PMP renewal

During year 4 – Q4 I have focused on the writing of books, and I still have to finish the English version of the “Cuaderno de trabajo para dibujar estrategias“. I will focus on Wardley Maps and completing my PMP renewal (I have 55 PDUs to complete). The plan So the V2MOM for this quarter will be: Vision: Work … Read more

## Box-cox transformation

These are reminder notes about Box-cox transformation. One of the problems that box-cox transformation tries to solve is “heteroscedasticity” (non-constant variance). This article explains the problem where you can apply box-cox transformation to solve it: https://blog.minitab.com/en/applying-statistics-in-quality-projects/how-could-you-benefit-from-a-box-cox-transformation SciPy has added an inverse Box-Cox transformation: https://docs.scipy.org/doc/scipy/reference/generated/scipy.special.inv_boxcox.html Does Box-cox always work? The answer is NO. Box-cox does not … Read more

## Time Series notes

I have done this course proposed by Kaggle, and I would like to take some notes. The trend component of a time series represents a persistent, long-term change in the mean of the series. We mainly have: Time dependent properties: trends and seasonality. Serial dependent properties: Cycles and lagged series 1. Trends The trend component of a time series … Read more

## Intermediate Machine Learning, by Kaggle

Some notes of this course offered by Kaggle, for my poor memory. Cross validation Cross-validation gives a more accurate measure of model quality, which is especially important if you are making a lot of modeling decisions.  Use pipelines for doing cross-validation, you will save a lot of time. XGBoost = Gradient boosting We refer to … Read more

## Cost of data exploitation

If you have a mine, the cost of obtaining a kilo of gold, aluminum, cooper or whatever, they all measure the cost of obtaining a kilo of the target element. With the machine learning projects, the situation is similar, and the definition of cost of data exploitation is something that should be defined from early … Read more

## Machine Learning, using LSTM to predict S&P 500

This post gather the analysis of data done with market breadth data, VIX, DIX and GEX. They are moved into a Long Short Term Memory (LSTM) neural network, that is a recurrent neural network. You can check the code and read how the whole thing is done. Input data The used features as input are: … Read more

## Looking for a machine learning model that hits S&P 500 daily change using market breadth data, DIX, GEX, VIX.

This is the third version of a code I have started to write while learning the concepts of Machine Learning. Changes with respect the previous versions Shift(-1) have been removed for the SPX price, I consider is an error to add it. I have added data related to DIX, GEX (since 2011) and VIX (since … Read more

## Data analysis on market breadth data

This post is an exercise to learn how to predict using different data on a machine learning model. Background Market breadth data and indicators are very popular in the investment world. I find them useful, and as I know them, I will use them as basis to experiment machine learning models. Data Analysis I have … Read more

## Using Machine Learning to predict the S&P 500 price change, using the dark pool indicators Dix and Gex

This is the first version of an analysis I wanted to perform with the main purpose of learning. By this reason I have limited the number of input data and operations to the minimum. To do something different I will be looking for correlations between the two main dark pool indexes: DIX and GEX Indexes. … Read more