# Load packages

# Core
library(tidyverse)
library(tidyquant)
library(scales)
library(ggrepel)

Goal

Visualize and examine changes in the underlying trend in the performance of your portfolio in terms of Sharpe Ratio.

Choose your stocks.

from 2012-12-31 to present

1 Import stock prices

symbols <- c("AMGN", "T", "BA", "CAT", "IBM")
prices <- tq_get(x    = symbols, 
                 get = "stock.prices",
                 from = "2012-12-31",
                 to   = "2022-11-03")

2 Convert prices to returns (monthly)

asset_returns_tbl <- prices %>%
    
    group_by(symbol) %>%
    
    tq_transmute(select     = adjusted, 
                 mutate_fun = periodReturn,
                 period     = "monthly", 
                 type       = "log") %>%
    
   slice(-1) %>%
    
    ungroup() %>%
    set_names(c("asset", "date", "returns"))

3 Assign a weight to each asset (change the weigting scheme)

symbols <- asset_returns_tbl %>% distinct(asset) %>% pull()
symbols
## [1] "AMGN" "BA"   "CAT"  "IBM"  "T"
#Weights
weights <- c(0.15, 0.50, 0.05, 0.1, 0.2)
weights
## [1] 0.15 0.50 0.05 0.10 0.20
w_tbl <- tibble(symbols, weights)
w_tbl
## # A tibble: 5 × 2
##   symbols weights
##   <chr>     <dbl>
## 1 AMGN       0.15
## 2 BA         0.5 
## 3 CAT        0.05
## 4 IBM        0.1 
## 5 T          0.2

4 Build a portfolio

# tq_portfolio

portfolio_returns_tbl <- asset_returns_tbl %>%
    
    tq_portfolio(assets_col   = asset, 
                 returns_col  = returns, 
                 weights      = w_tbl, 
                 rebalance_on = "months", 
                 col_rename   = "returns" )

portfolio_returns_tbl
## # A tibble: 119 × 2
##    date        returns
##    <date>        <dbl>
##  1 2013-01-31  0.00894
##  2 2013-02-28  0.0369 
##  3 2013-03-28  0.0793 
##  4 2013-04-30  0.0350 
##  5 2013-05-31  0.0280 
##  6 2013-06-28  0.00605
##  7 2013-07-31  0.0320 
##  8 2013-08-30 -0.0167 
##  9 2013-09-30  0.0675 
## 10 2013-10-31  0.0722 
## # … with 109 more rows

5 Compute Sharpe Ratio

# Define rfr
rfr <- .0003 

portfolio_SharpeRatio_tbl <- portfolio_returns_tbl %>%
    tq_performance(Ra              = returns, 
                   performance_fun = SharpeRatio,
                   Rf              = rfr, 
                   FUN             = "StdDev")
portfolio_SharpeRatio_tbl
## # A tibble: 1 × 1
##   `StdDevSharpe(Rf=0%,p=95%)`
##                         <dbl>
## 1                      0.0933

6 Plot: Rolling Sharpe Ratio

# Create custom function to calculate rolling SR
calculate_rolling_SharpeRatio <- function(data) {
    
    rolling_SR <- SharpeRatio(R = data, Rf = rfr, FUN = "StdDev")
    
    return(rolling_SR)
}
# Define Window
window <- 24
# Transform data: Calculate Rolling Sharpe Ratio

rolling_sr_tbl <- portfolio_returns_tbl %>%
    
   tq_mutate(select = returns, 
             mutate_fun = rollapply,
             width = window,
             FUN = calculate_rolling_SharpeRatio, 
             col_rename = "rolling_sr") %>%
    select(-returns) %>%
    na.omit()


rolling_sr_tbl
## # A tibble: 96 × 2
##    date       rolling_sr
##    <date>          <dbl>
##  1 2014-12-31      0.516
##  2 2015-01-30      0.550
##  3 2015-02-27      0.556
##  4 2015-03-31      0.466
##  5 2015-04-30      0.424
##  6 2015-05-29      0.371
##  7 2015-06-30      0.349
##  8 2015-07-31      0.353
##  9 2015-08-31      0.220
## 10 2015-09-30      0.119
## # … with 86 more rows
rolling_sr_tbl %>%
    ggplot(aes(x = date, y = rolling_sr)) +
    geom_line(color = "cornflowerblue") +
    
    # labeling
    labs(x = NULL, y = "Rolling Sharpe Ratio") +
    annotate(geom = "text", x = as.Date("2016-6-01"), y = .7, label = "This portfolio has 
been quite volitile.", color = "red", size = 4)

How has your portfolio performed over time? Provide dates of the structural breaks, if any. The Code Along Assignment 9 had one structural break in November 2016. What do you think the reason is?

There seems to have been a structural break around March of the year 2020. This might have been due to the Coronavirus outbreak in the United States. The structural break in code along assignment 9 might have been due to the upcoming presidential election at the time. Overall, the portfolio has been highly volatile over the time frame being measured. Shortly after 2018, the portfolio peaked and had a fairly good return compared to the risk being assumed. In the last couple of years the portfolio hasn’t performed very well at all however.