diff --git a/NAMESPACE b/NAMESPACE
index 874a4980b..40f1799c4 100644
--- a/NAMESPACE
+++ b/NAMESPACE
@@ -3,6 +3,7 @@
 export("%>%")
 export(add_homelessness_date_flags)
 export(add_homelessness_flag)
+export(add_hri_variables)
 export(add_nsu_cohort)
 export(check_year_format)
 export(clean_up_free_text)
diff --git a/R/add_hri_variables.R b/R/add_hri_variables.R
new file mode 100644
index 000000000..320b6222e
--- /dev/null
+++ b/R/add_hri_variables.R
@@ -0,0 +1,141 @@
+#' Flag non-Scottish residents
+#'
+#' @details The variable keep flag can be in the range c(0:4) where
+#' \itemize{
+#' \item{keep_flag = 0 when resident is Scottish}
+#' \item{keep_flag = 1 when resident is not Scottish}
+#' \item{keep_flag = 2 when the postcode is missing or a dummy, and the gpprac is missing}
+#' \item{keep_flag = 3 when the gpprac is not English and the postcode is missing}
+#' \item{keep_flag = 4 when the gpprac is not English and the postcode is a dummy}
+#' }
+#' The intention is to only keep the records where keep_flag = 0
+#'
+#' @inheritParams add_hri_variables
+#'
+#' @return A data frame with the variable 'keep_flag'
+flag_non_scottish_residents <- function(
+    data,
+    slf_pc_lookup) {
+  check_variables_exist(data, c("postcode", "gpprac"))
+
+  # Make a lookup of postcode areas, which consist of the first characters
+  # of the postcode
+  pc_areas <- slf_pc_lookup %>%
+    dplyr::mutate(
+      pc_area = stringr::str_match(postcode, "^[A-Z]{1,3}"),
+      scot_flag = TRUE
+    ) %>%
+    dplyr::distinct(pc_area, scot_flag)
+
+  # Create a flag, 'keep_flag', to determine whether individuals are Scottish
+  # residents or not
+  return_data <- data %>%
+    dplyr::mutate(pc_area = stringr::str_match(postcode, "^[A-Z]{1,3}")) %>%
+    dplyr::left_join(pc_areas, by = "pc_area") %>%
+    dplyr::mutate(
+      dummy_postcode = .data$postcode %in% c("BF010AA", "NF1 1AB", "NK010AA") |
+        stringr::str_sub(.data$postcode, 1, 4) %in% c("ZZ01", "ZZ61"),
+      eng_prac = .data$gpprac %in% c(99942, 99957, 99961, 99976, 99981, 99995, 99999),
+      scottish_resident = dplyr::case_when(
+        .data$scot_flag ~ 0L,
+        (is_missing(.data$postcode) | .data$dummy_postcode) & is.na(.data$gpprac) ~ 2L,
+        !.data$eng_prac & is_missing(.data$postcode) ~ 3L,
+        !.data$eng_prac & .data$dummy_postcode ~ 4L,
+        .default = 1L
+      )
+    ) %>%
+    dplyr::select(-"dummy_postcode", -"eng_prac")
+
+  return(return_data)
+}
+
+#' Add HRI variables to an SLF Individual File
+#'
+#' @details Filters the dataset to only include Scottish residents, then
+#' creates a lookup where HRIs are calculated at Scotland, Health Board, and
+#' LCA level. Then joins on this lookup by chi/anon_chi.
+#'
+#' @param data An SLF individual file.
+#' @param slf_pc_lookup The Source postcode lookup, defaults
+#' to [get_slf_postcode_path()] read using [read_file()].
+#'
+#' @return The individual file with HRI variables matched on
+#' @export
+add_hri_variables <- function(
+    data,
+    slf_pc_lookup = read_file(
+      get_slf_postcode_path(),
+      col_select = "postcode"
+    )) {
+  hri_lookup <- data %>%
+    dplyr::select(
+      "year",
+      "chi",
+      "postcode",
+      "gpprac",
+      "lca",
+      "hbrescode",
+      "health_net_cost",
+      "acute_episodes",
+      "mat_episodes",
+      "mh_episodes",
+      "gls_episodes",
+      "op_newcons_attendances",
+      # op_newcons_dnas,
+      "ae_attendances",
+      "pis_paid_items",
+      "ooh_cases"
+    ) %>%
+    flag_non_scottish_residents(slf_pc_lookup = slf_pc_lookup) %>%
+    dplyr::filter(scottish_resident == 0L) %>%
+    # Scotland cost and proportion
+    dplyr::mutate(
+      scotland_cost = sum(health_net_cost),
+      scotland_pct = (health_net_cost / scotland_cost) * 100
+    ) %>%
+    dplyr::arrange(dplyr::desc(health_net_cost)) %>%
+    dplyr::mutate(hri_scotp = cumsum(scotland_pct)) %>%
+    # Health Board
+    dplyr::group_by(hbrescode) %>%
+    dplyr::mutate(
+      hb_cost = sum(health_net_cost),
+      hb_pct = (health_net_cost / hb_cost) * 100
+    ) %>%
+    dplyr::arrange(dplyr::desc(health_net_cost), .by_group = TRUE) %>%
+    dplyr::mutate(hri_hbp = cumsum(hb_pct)) %>%
+    dplyr::ungroup() %>%
+    # LCA
+    dplyr::group_by(lca) %>%
+    dplyr::mutate(
+      lca_cost = sum(health_net_cost),
+      lca_pct = (health_net_cost / lca_cost) * 100
+    ) %>%
+    dplyr::arrange(dplyr::desc(health_net_cost), .by_group = TRUE) %>%
+    dplyr::mutate(hri_lcap = cumsum(lca_pct)) %>%
+    dplyr::ungroup() %>%
+    # Add HRI flags
+    dplyr::mutate(
+      hri_scot = hri_scotp <= 50.0,
+      hri_hb = hri_hbp <= 50.0,
+      hri_lca = hri_lcap <= 50.0,
+      # Deal with potential missing variables
+      hri_hb = dplyr::if_else(is_missing(hbrescode), FALSE, hri_hb),
+      hri_hbp = dplyr::if_else(is_missing(hbrescode), NA, hri_hbp),
+      hri_lca = dplyr::if_else(is_missing(lca), FALSE, hri_lca),
+      hri_lcap = dplyr::if_else(is_missing(lca), NA, hri_lcap)
+    ) %>%
+    # Select only required variables for the lookup
+    dplyr::select(
+      chi_variable,
+      "hri_scot",
+      "hri_scotp",
+      "hri_hb",
+      "hri_hbp",
+      "hri_lca",
+      "hri_lcap"
+    )
+
+  return_data <- dplyr::left_join(data, hri_lookup, by = chi_variable)
+
+  return(return_data)
+}
diff --git a/man/add_hri_variables.Rd b/man/add_hri_variables.Rd
new file mode 100644
index 000000000..d35464357
--- /dev/null
+++ b/man/add_hri_variables.Rd
@@ -0,0 +1,28 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/add_hri_variables.R
+\name{add_hri_variables}
+\alias{add_hri_variables}
+\title{Add HRI variables to an SLF Individual File}
+\usage{
+add_hri_variables(
+  data,
+  slf_pc_lookup = read_file(get_slf_postcode_path(), col_select = "postcode")
+)
+}
+\arguments{
+\item{data}{An SLF individual file.}
+
+\item{slf_pc_lookup}{The Source postcode lookup, defaults
+to \code{\link[=get_slf_postcode_path]{get_slf_postcode_path()}} read using \code{\link[=read_file]{read_file()}}.}
+}
+\value{
+The individual file with HRI variables matched on
+}
+\description{
+Add HRI variables to an SLF Individual File
+}
+\details{
+Filters the dataset to only include Scottish residents, then
+creates a lookup where HRIs are calculated at Scotland, Health Board, and
+LCA level. Then joins on this lookup by chi/anon_chi.
+}
diff --git a/man/flag_non_scottish_residents.Rd b/man/flag_non_scottish_residents.Rd
new file mode 100644
index 000000000..ec97dedf6
--- /dev/null
+++ b/man/flag_non_scottish_residents.Rd
@@ -0,0 +1,31 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/add_hri_variables.R
+\name{flag_non_scottish_residents}
+\alias{flag_non_scottish_residents}
+\title{Flag non-Scottish residents}
+\usage{
+flag_non_scottish_residents(data, slf_pc_lookup)
+}
+\arguments{
+\item{data}{An SLF individual file.}
+
+\item{slf_pc_lookup}{The Source postcode lookup, defaults
+to \code{\link[=get_slf_postcode_path]{get_slf_postcode_path()}} read using \code{\link[=read_file]{read_file()}}.}
+}
+\value{
+A data frame with the variable 'keep_flag'
+}
+\description{
+Flag non-Scottish residents
+}
+\details{
+The variable keep flag can be in the range c(0:4) where
+\itemize{
+\item{keep_flag = 0 when resident is Scottish}
+\item{keep_flag = 1 when resident is not Scottish}
+\item{keep_flag = 2 when the postcode is missing or a dummy, and the gpprac is missing}
+\item{keep_flag = 3 when the gpprac is not English and the postcode is missing}
+\item{keep_flag = 4 when the gpprac is not English and the postcode is a dummy}
+}
+The intention is to only keep the records where keep_flag = 0
+}
diff --git a/tests/testthat/test-flag_non_scottish_residents.R b/tests/testthat/test-flag_non_scottish_residents.R
new file mode 100644
index 000000000..b61d9e159
--- /dev/null
+++ b/tests/testthat/test-flag_non_scottish_residents.R
@@ -0,0 +1,26 @@
+test_that("Records are flagged correctly", {
+  test_frame <- tibble::tribble(
+    ~postcode, ~gpprac,
+    # Scottish resident
+    "AB1 1AA", 18574,
+    # Dummy postcode and missing gpprac
+    "BF010AA", NA,
+    # Dummy postcode and missing gpprac (2)
+    "ZZ014AA", NA,
+    # Missing postcode and missing gpprac
+    NA, NA,
+    # Not English practice and missing postcode
+    NA, 18574,
+    # Not English practice and dummy postcode
+    "NF1 1AB", 18574,
+    # English postcode and English gpprac
+    "BS4 4RG", 99942
+  )
+
+  test_frame_flagged <- flag_non_scottish_residents(test_frame)
+
+  expect_equal(
+    test_frame_flagged$keep_flag,
+    c(0, 2, 2, 2, 3, 4, 1)
+  )
+})