# Load packages

# Core
library(tidyverse)
library(tidyquant)

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 ("DLR", "NVDA", "GOOG", "MSFT", "AMZN")

prices <- tq_get(x = symbols,
                 get = "stockprices",
                 from = "2012-12-31",
                 to = "2026-11-02")

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
symbols <- asset_returns_tbl %>% distinct(asset) %>% pull()
symbols
## [1] "AMZN" "DLR"  "GOOG" "MSFT" "NVDA"
# weights
weights <- c(0.2, 0.2, 0.2, 0.2, 0.2)
weights 
## [1] 0.2 0.2 0.2 0.2 0.2
w_tbl <- tibble(symbols, weights)
w_tbl
## # A tibble: 5 × 2
##   symbols weights
##   <chr>     <dbl>
## 1 AMZN        0.2
## 2 DLR         0.2
## 3 GOOG        0.2
## 4 MSFT        0.2
## 5 NVDA        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 = "quarters",
               col_rename = "returns")

portfolio_returns_tbl
## # A tibble: 166 × 2
##    date        returns
##    <date>        <dbl>
##  1 2013-01-31  0.0301 
##  2 2013-02-28  0.0201 
##  3 2013-03-28  0.0101 
##  4 2013-04-30  0.0516 
##  5 2013-05-31  0.0164 
##  6 2013-06-28  0.00167
##  7 2013-07-31 -0.0124 
##  8 2013-08-30 -0.00816
##  9 2013-09-30  0.0336 
## 10 2013-10-31  0.0489 
## # ℹ 156 more rows

5 Compute Sharpe Ratio

# Define risk free rate
rfr <- 0.0003

portfolio_SharpeRatio_tbl <- portfolio_returns_tbl %>%
  
  tq_performance(Ra = returns, 
                 performance_fun = SharpeRatio, 
                 Rf = rfr,
                 FUN = "StdDev")

portfolio_SharpeRatio_tbl
## # A tibble: 1 × 1
##   `SharpeRatio(Rf=0%,p=95%)`
##                        <dbl>
## 1                      0.337

Scatterplot of Returns around Risk Free Rate

portfolio_returns_tbl %>%
  
  # Add a new variable
  mutate(excess_returns = if_else(returns > rfr,
                                  "rfr_above",
                                  "rfr_below")) %>%
  # Plot
  ggplot(aes(x = date, y = returns)) +
  geom_point(aes(color = excess_returns)) + 
  geom_hline(yintercept = rfr, color = "cornflowerblue", linetype = 3, size = 1) +
  geom_vline(xintercept = as.Date("2019-02-19"),
             color = "cornflowerblue", size = 1, alpha = 0.5) +
  
  theme(legend.position = "none") +
  
  annotate(geom = "text", 
           x = as.Date("2019-06-19"), y = -0.05, 
           label = "Covid", size = 5, angle = 90) +
             
  annotate(geom = "text", 
           x = as.Date("2015-09-01"), y = -0.13, 
           label = str_glue("More volatile after COVID, 
                            with more of negative returns."), 
           color = "green") +
             
  labs(y = "monthly returns", x = NULL)

## 6 Plot: Rolling Sharpe Ratio

# Create a 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: 143 × 2
##    date       rolling_sr
##    <date>          <dbl>
##  1 2014-12-31      0.522
##  2 2015-01-30      0.499
##  3 2015-02-27      0.524
##  4 2015-03-31      0.441
##  5 2015-04-30      0.446
##  6 2015-05-29      0.427
##  7 2015-06-30      0.372
##  8 2015-07-31      0.458
##  9 2015-08-31      0.463
## 10 2015-09-30      0.456
## # ℹ 133 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("2018-03-01"), y = 0.08,
           label = "This portfolio has mostly positive returns, 
           with one small negative period during the COVID period. 
           However, since the start of COVID, the portfolio has been
           more volatile.", 
           color = "red", size = 2.75)

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? My portfolio, made up of equal weights in DLR, NVDA, GOOG, MSFT, and AMZN, performed fairly steadily through 2015 and most of 2016, with the rolling Sharpe ratio staying around 0.4 to 0.5. There is a clear change around late 2016, when the Sharpe ratio started increasing quickly through 2017. I think this was partly due to the shift toward big tech and cloud growth, which benefited these companies. Another major change happened around March 2020 with the start of COVID. The portfolio became much more volatile after COVID, with bigger negative dips but also higher return spikes. The mean return increased as demand for tech grew during lockdowns, pushing the Sharpe ratio back above 0.8. However, the higher volatility also caused bigger swings, including the drop around 2022 and the strong rebound afterward.