estimate_daily_arfima_forecasts.R

# Set the number of cores to be used for parallelize the ARFIMA estimation
nCores <- detectCores() - 1

# A function to estimate the ARFIMA model
arfima_func <- function(data) {

  # Estimate the ARFIMA model
  arfima_fit <- autoarfima(data, ar.max = 5, ma.max = 5, criterion = "BIC", method = "partial", 
                           arfima = TRUE, include.mean = TRUE, cluster = cluster, 
                           distribution.model = "norm", solver = "hybrid", return.all = FALSE)
  return(arfima_fit)
}

# A function to stop runningn the ARFIMA model in case it takes more 10 minutes to run
myWrapperFunction <- function(data) {
  result = tryCatch(expr = withTimeout(arfima_func(data), timeout = 10*60), 
            TimeoutException = function(ex) "TimedOut")
  return(result)
}

# The for loop to estimate the ARFIMA model each day
for (i in (initial_iloc_to_forecast):nrow(data)) {
  start_time <- Sys.time()

  # Select the corresponding 6-year previous data to train the ARFIMA model
  #data_sample <- subset(data, !(data$date %in% dates_to_be_removed)) 
  data_sample <- data$AAPL[((i-1)-(span-1)):(i-1)]
  
  # Print some days info
  print(paste0(strrep('=',50)))
  print(paste0("Forecast ",(i+1-initial_iloc_to_forecast), ' out of ', length(df_forecasts$date)))
  
  # Make the cluster based on the previous number of cores
  cluster <- makePSOCKcluster(nCores)
  
  # Estimate the ARFIMA model for this day
  arfima_fit <- myWrapperFunction(data_sample)
  
  # Stop the CPU multithreading
  stopCluster(cluster) 
  
  if (typeof(arfima_fit)!="list") {

    # Print a statement saying estimtation took too long
    print(paste0("Estimation took longer than expected. Today's signal will be 0."))
    
    # Signal will be 0 this day
    df_forecasts[(i+1-initial_iloc_to_forecast),'signal'] <- 0.0
    
    # Save the df_forecasts in an excel file
    write.xlsx(df_forecasts, 'df_forecasts_in_R_v01.xlsx')
    
    # Print some important things for log
    print(paste0("Date is ",df_forecasts[(i+1-initial_iloc_to_forecast),]$date))
    print(paste0("Signal is ",df_forecasts[(i+1-initial_iloc_to_forecast),'signal']))
    print(paste0("Start time is ",start_time))
    end_time <- Sys.time()
    print(paste0("End time is ",end_time))
    
    #calculate time difference in minutes
    diff <- difftime(end_time, start_time, units="mins")
    print(paste0("Time passed is ",round(diff,2)," minutes"))
  } else {
    # Obtain the data sample Apple last price
    last_apple_price <- tail(data_sample,1)[[1]]
    
    # Forecast the next day Apple stock close price forecast
    forecast <- arfimaforecast(arfima_fit$fit, data=data_sample, n.ahead=1)@forecast$seriesFor[1]
    
    # Go long if the forecast is higher than the previous-day stock close price
    df_forecasts[(i+1-initial_iloc_to_forecast),'signal'] <- if (forecast>=last_apple_price) 1 else 0  
    
    # Save the df_forecasts in an excel file
    write.xlsx(df_forecasts, 'df_forecasts_in_R_v01.xlsx')
    
    print(paste0("Date is ",df_forecasts[(i+1-initial_iloc_to_forecast),]$date))
    print(paste0('Price forecast is ',forecast))
    print(paste0('Last AAPL price is ',last_apple_price))
    print(paste0("Signal is ",df_forecasts[(i+1-initial_iloc_to_forecast),'signal']))
    print(paste0("Start time is ",start_time))
    end_time <- Sys.time()
    print(paste0("End time is ",end_time))
    
    #calculate time difference in minutes
    diff <- difftime(end_time, start_time, units="mins")
    print(paste0("Time passed is ",round(diff,2)," minutes"))
  }
}