lazytrade (version 0.4.0)

mt_make_model: Function to train Deep Learning Classification model for Market Type recognition

Description

Function is training h2o deep learning model to match manually classified patterns of the financial indicator. Main idea is to be able to detect Market Type by solely relying on the current indicator pattern. This is in the attempt to evaluate current market type and to use proper trading strategy.

Selected Market Periods according to the theory from Van K. Tharp: 1. Bull normal, BUN 2. Bull volatile, BUV 3. Bear normal, BEN 4. Bear volatile, BEV 5. Sideways quiet, RAN 6. Sideways volatile, RAV

Usage

mt_make_model(indicator_dataset, num_bars, path_model, path_data)

Arguments

indicator_dataset

Dataset containing indicator patterns to train the model

num_bars

Number of bars used to detect pattern

path_model

Path where the models are be stored

path_data

Path where the aggregated historical data is stored, if exists in rds format

Value

Function is writing file object with the model

Details

Function is using manually prepared dataset and tries several different random neural network structures. Once the best neural network is found then the better model is trained and stored.

Examples

# NOT RUN {
# }
# NOT RUN {
library(dplyr)
library(magrittr)
library(readr)
library(h2o)
library(lazytrade)

path_model <- normalizePath(tempdir(),winslash = "/")
path_data <- normalizePath(tempdir(),winslash = "/")

data(macd_ML2)

Sys.sleep(5)

# start h2o engine (using all CPU's by default)
h2o.init()


# performing Deep Learning Regression using the custom function
mt_make_model(indicator_dataset = macd_ML2,
              num_bars = 64,
              path_model = path_model,
              path_data = path_data)

# stop h2o engine
h2o.shutdown(prompt = FALSE)

#set delay to insure h2o unit closes properly before the next test
Sys.sleep(5)

# }
# NOT RUN {


# }