Trading Strategies using R - Algorithm Trading - Quantitative Finance - ...

Python for Data Science - Machine Learning Module

 

Registration Link:  https://forms.gle/ovQ3F1uDShDyoDhT6

Please Share with your colleagues, friends, and other interested participants.

Thanks

Rajesh Prabhakar Kaila

Mobile - 90009 61141

Email - krpresearch@gmail.com

R Shiny Application for Forecasting Share Prices using ARIMA

The Application downloads share price data from Yahoo Finance and uses the data to plot a Candle stick chart with Relative Strength Index (RSI) Indicator.

Interpretation of RSI:

a) RSI falls into Oversold Category if it falls below 30%
b) RSI falls into Overbought Category if it raises above 70%
c) The RSI calculates average price gains and losses over a given period of time; the default time period is 14 periods with values bounded from 0 to 100.

Just Copy & Paste the code in R Shiny App in R Studio as App.R or separately ui in ui.R and server in server.R

Please be careful in regards to indentation.

R Shiny Application Link:  https://krpresearch.shinyapps.io/stockprediction/




R Shiny App Code:

library(shiny)

library(quantmod)

library(fpp)

ui=fluidPage(

  titlePanel("StockPrediction"),

  sidebarLayout(

    sidebarPanel(

      helpText("Select Ticker Yahoo Finance"),

      textInput("symb","Symbol","GOOG"),

      dateRangeInput("dates",

                     "Date Range",

                     start="2007-01-01",

                     end=as.character(Sys.Date())),

      br(),

      br()

    ),

    mainPanel(plotOutput("technical"),plotOutput("summary"))

  )

)

server=function(input,output){

  dataInput=reactive({

    getSymbols(input$symb,from=input$dates[1],

               to=input$dates[2],auto.assign = F)

    

  })

  output$technical=renderPlot({

    data=dataInput()

    chartSeries(data,type="candlesticks")

    addBBands()

    addRSI()

  })

  output$summary=renderPlot({

    datadf=as.data.frame(dataInput())

    dataclose=datadf[,4]

    dataclose=na.omit(dataclose)

    fit=auto.arima(ts(dataclose,frequency = 7),D=1)

    summary(fit)

    plot(forecast(fit,h=50))

    

  })

  

}

shinyApp(ui=ui,server=server)