# 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 ("GS", "NVDA", "JPM", "MS", "BAC")

prices <- tq_get(x = symbols,
                 get = "stockprices",
                 from = "2012-12-31",
                 to = "2017-12-31")

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] "BAC"  "GS"   "JPM"  "MS"   "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 BAC         0.2
## 2 GS          0.2
## 3 JPM         0.2
## 4 MS          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: 60 × 2
##    date        returns
##    <date>        <dbl>
##  1 2013-01-31  0.0750 
##  2 2013-02-28  0.0147 
##  3 2013-03-28  0.00152
##  4 2013-04-30  0.0245 
##  5 2013-05-31  0.105  
##  6 2013-06-28 -0.0500 
##  7 2013-07-31  0.0814 
##  8 2013-08-30 -0.0468 
##  9 2013-09-30  0.0273 
## 10 2013-10-31  0.0150 
## # ℹ 50 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                      0.396

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)

# 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: 37 × 2
##    date       rolling_sr
##    <date>          <dbl>
##  1 2014-12-31      0.517
##  2 2015-01-30      0.264
##  3 2015-02-27      0.315
##  4 2015-03-31      0.294
##  5 2015-04-30      0.310
##  6 2015-05-29      0.267
##  7 2015-06-30      0.323
##  8 2015-07-31      0.270
##  9 2015-08-31      0.269
## 10 2015-09-30      0.212
## # ℹ 27 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 = "Between 2015 to mid year 2016 this portfolio saw signifigant loss. However, since then the portfolio has made a signifigant bounce back into 2018", 
           color = "red", size = 2.75)

6 Plot: Rolling Sharpe Ratio

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’s performance has changed over time, with periods of both strong and weak returns. The overall Sharpe Ratio was 0.396, which shows that the portfolio earned a positive return relative to the amount of risk taken. The rolling Sharpe Ratio was higher at the end of 2014 but decreased during 2015 and early 2016. This suggests the portfolio was not performing as well compared to its risk. Performance improved afterward as the portfolio recovered.

One possible structural break was around November 2016, when the U.S. presidential election caused changes in market expectations. Since my portfolio includes financial stocks like Goldman Sachs, JPMorgan, Morgan Stanley, and Bank of America, expectations of higher interest rates and fewer banking regulations could have helped performance.