diff --git a/R/helpers.R b/R/helpers.R
index 3f23fd7..e8342f2 100644
--- a/R/helpers.R
+++ b/R/helpers.R
@@ -137,10 +137,10 @@ select_iterations <- function(tune_results, metric, type = "mean") {
 # to numbers
 var_encode <- function(data,
                        cols = dplyr::everything(),
-                       dict = ccao::vars_dict) {
+                       dictionary = ccao::vars_dict) {
   var <- "var_code"
 
-  dict_long <- dict %>%
+  dict_long <- dictionary %>%
     dplyr::filter(
       .data$var_type == "char" &
         .data$var_data_type == "categorical"
diff --git a/dvc.lock b/dvc.lock
index 18e4bab..62d58f4 100644
--- a/dvc.lock
+++ b/dvc.lock
@@ -2,6 +2,11 @@ schema: '2.0'
 stages:
   ingest:
     cmd: Rscript pipeline/00-ingest.R
+    deps:
+    - path: pipeline/00-ingest.R
+      hash: md5
+      md5: 29292ee2bef109914c423c9259aa8879
+      size: 22847
     params:
       params.yaml:
         assessment:
@@ -26,24 +31,24 @@ stages:
     outs:
     - path: input/assessment_data.parquet
       hash: md5
-      md5: 605ee612ff45dca2edf5c508993a7f56
-      size: 69522635
+      md5: b49601e8a812659026c7358d84f5e16b
+      size: 85702121
     - path: input/char_data.parquet
       hash: md5
-      md5: ed7b8f4ed02eb491d0450920874a66c3
-      size: 131476800
+      md5: d1a30dd51db2985be57548c1498f2533
+      size: 160972976
     - path: input/condo_strata_data.parquet
       hash: md5
-      md5: 0a7462f0afccb09bdd94c58148a3ca8d
-      size: 40842
+      md5: 8fe86e0af29431ecb021f101f79789ee
+      size: 40481
     - path: input/land_nbhd_rate_data.parquet
       hash: md5
-      md5: e508daf5790982c303d6503fe1cb8e2b
-      size: 4413
+      md5: f3ec9627322bd271bf2957b7388aaa34
+      size: 3873
     - path: input/training_data.parquet
       hash: md5
-      md5: 51090aa4f5b5311b1441e62b81fd3827
-      size: 68987740
+      md5: 9b2510ac885e4fc77928661a012d8821
+      size: 79812730
   train:
     cmd: Rscript pipeline/01-train.R
     deps:
@@ -872,8 +877,8 @@ stages:
           - loc_school_elementary_district_geoid
           - loc_school_secondary_district_geoid
           - loc_school_unified_district_geoid
-        run_note: "Test run for updated 2024 model pipeline. Remove CCAO collected
-          characteristics.\n"
+        run_note: "Test run for updated 2024 model pipeline. Remove CCAO collected\
+          \ characteristics.\n"
         toggle:
           cv_enable: false
           shap_enable: false
diff --git a/pipeline/00-ingest.R b/pipeline/00-ingest.R
index 937279d..667a0ee 100644
--- a/pipeline/00-ingest.R
+++ b/pipeline/00-ingest.R
@@ -19,6 +19,9 @@ suppressPackageStartupMessages({
   library(noctua)
 })
 
+# Adds arrow support to speed up ingest process
+noctua_options(unload = TRUE)
+
 # Establish Athena connection
 AWS_ATHENA_CONN_NOCTUA <- dbConnect(
   noctua::athena(),
@@ -139,8 +142,8 @@ col_type_dict <- ccao::vars_dict %>%
   drop_na(var_name)
 
 # Mini-function to ensure that columns are the correct type
-recode_column_type <- function(col, col_name, dict = col_type_dict) {
-  col_type <- dict %>%
+recode_column_type <- function(col, col_name, dictionary = col_type_dict) {
+  col_type <- dictionary %>%
     filter(var_name == col_name) %>%
     pull(var_type)
 
@@ -214,6 +217,30 @@ rescale <- function(x, min = 0, max = 1) {
 }
 
 
+# Mini function to deal with arrays
+# Some Athena columns are stored as arrays but are converted to string on
+# ingest. In such cases, we either keep the contents of the cell (if 1 unit),
+# collapse the array into a comma-separated string (if more than 1 unit),
+# or replace with NA if the array is empty
+process_array_columns <- function(data, selector) {
+  data %>%
+    mutate(
+      across(
+        !!enquo(selector),
+        ~ sapply(.x, function(cell) {
+          if (length(cell) > 1) {
+            paste(cell, collapse = ", ")
+          } else if (length(cell) == 1) {
+            as.character(cell) # Convert the single element to character
+          } else {
+            NA # Handle cases where the array is empty
+          }
+        })
+      )
+    )
+}
+
+
 
 
 #- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
@@ -283,7 +310,7 @@ training_data_clean <- training_data_fil %>%
   # Recode factor variables using the definitions stored in ccao::vars_dict
   # This will remove any categories not stored in the dictionary and convert
   # them to NA (useful since there are a lot of misrecorded variables)
-  ccao::vars_recode(cols = starts_with("char_"), type = "code") %>%
+  ccao::vars_recode(cols = starts_with("char_"), code_type = "code") %>%
   # Coerce columns to the data types recorded in the dictionary. Necessary
   # because the SQL drivers will often coerce types on pull (boolean becomes
   # character)
@@ -324,10 +351,13 @@ training_data_clean <- training_data_fil %>%
   ) %>%
   # Some Athena columns are stored as arrays but are converted to string on
   # ingest. In such cases, take the first element and clean the string
+  # Apply the helper function to process array columns
+  process_array_columns(starts_with("loc_tax_")) %>%
+  mutate(
+    loc_tax_municipality_name =
+      replace_na(loc_tax_municipality_name, "UNINCORPORATED")
+  ) %>%
   mutate(
-    across(starts_with("loc_tax_"), \(x) str_replace_all(x, "\\[|\\]", "")),
-    across(starts_with("loc_tax_"), \(x) str_trim(str_split_i(x, ",", 1))),
-    across(starts_with("loc_tax_"), \(x) na_if(x, "")),
     # Miscellanous column-level cleanup
     ccao_is_corner_lot = replace_na(ccao_is_corner_lot, FALSE),
     ccao_is_active_exe_homeowner = replace_na(ccao_is_active_exe_homeowner, 0L),
@@ -377,16 +407,19 @@ training_data_clean <- training_data_fil %>%
 # used on. The cleaning steps are the same as above, with the exception of the
 # time variables
 assessment_data_clean <- assessment_data %>%
-  ccao::vars_recode(cols = starts_with("char_"), type = "code") %>%
+  ccao::vars_recode(cols = starts_with("char_"), code_type = "code") %>%
+  # Apply the helper function to process array columns
+  process_array_columns(starts_with("loc_tax_")) %>%
+  mutate(
+    loc_tax_municipality_name =
+      replace_na(loc_tax_municipality_name, "UNINCORPORATED")
+  ) %>%
   mutate(across(
     any_of(col_type_dict$var_name),
     ~ recode_column_type(.x, cur_column())
   )) %>%
   # Same Athena string cleaning and feature cleanup as the training data
   mutate(
-    across(starts_with("loc_tax_"), \(x) str_replace_all(x, "\\[|\\]", "")),
-    across(starts_with("loc_tax_"), \(x) str_trim(str_split_i(x, ",", 1))),
-    across(starts_with("loc_tax_"), \(x) na_if(x, "")),
     ccao_is_active_exe_homeowner = replace_na(ccao_is_active_exe_homeowner, 0L),
     ccao_n_years_exe_homeowner = replace_na(ccao_n_years_exe_homeowner, 0L),
     across(where(is.character), \(x) na_if(x, "")),
diff --git a/renv/profiles/dev/renv.lock b/renv/profiles/dev/renv.lock
index d96fcea..567adbb 100644
--- a/renv/profiles/dev/renv.lock
+++ b/renv/profiles/dev/renv.lock
@@ -41,7 +41,7 @@
       "Package": "R6",
       "Version": "2.5.1",
       "Source": "Repository",
-      "Repository": "RSPM",
+      "Repository": "CRAN",
       "Requirements": [
         "R"
       ],
@@ -58,6 +58,16 @@
       ],
       "Hash": "6b868847b365672d6c1677b1608da9ed"
     },
+    "askpass": {
+      "Package": "askpass",
+      "Version": "1.2.1",
+      "Source": "Repository",
+      "Repository": "CRAN",
+      "Requirements": [
+        "sys"
+      ],
+      "Hash": "c39f4155b3ceb1a9a2799d700fbd4b6a"
+    },
     "base64enc": {
       "Package": "base64enc",
       "Version": "0.1-3",
@@ -175,6 +185,27 @@
       ],
       "Hash": "859d96e65ef198fd43e82b9628d593ef"
     },
+    "curl": {
+      "Package": "curl",
+      "Version": "6.0.1",
+      "Source": "Repository",
+      "Repository": "CRAN",
+      "Requirements": [
+        "R"
+      ],
+      "Hash": "e8ba62486230951fcd2b881c5be23f96"
+    },
+    "data.table": {
+      "Package": "data.table",
+      "Version": "1.16.4",
+      "Source": "Repository",
+      "Repository": "CRAN",
+      "Requirements": [
+        "R",
+        "methods"
+      ],
+      "Hash": "38bbf05fc2503143db4c734a7e5cab66"
+    },
     "digest": {
       "Package": "digest",
       "Version": "0.6.37",
@@ -290,9 +321,24 @@
       ],
       "Hash": "81d371a9cc60640e74e4ab6ac46dcedc"
     },
+    "httr": {
+      "Package": "httr",
+      "Version": "1.4.7",
+      "Source": "Repository",
+      "Repository": "RSPM",
+      "Requirements": [
+        "R",
+        "R6",
+        "curl",
+        "jsonlite",
+        "mime",
+        "openssl"
+      ],
+      "Hash": "ac107251d9d9fd72f0ca8049988f1d7f"
+    },
     "igraph": {
       "Package": "igraph",
-      "Version": "2.1.1",
+      "Version": "2.1.2",
       "Source": "Repository",
       "Repository": "CRAN",
       "Requirements": [
@@ -311,7 +357,7 @@
         "utils",
         "vctrs"
       ],
-      "Hash": "c03878b48737a0e2da3b772d7b2e22da"
+      "Hash": "9a93b743b2461ba06ba3b5df12011145"
     },
     "jquerylib": {
       "Package": "jquerylib",
@@ -424,8 +470,13 @@
     "noctua": {
       "Package": "noctua",
       "Version": "2.6.2",
-      "Source": "Repository",
-      "Repository": "CRAN",
+      "Source": "GitHub",
+      "RemoteType": "github",
+      "RemoteHost": "api.github.com",
+      "RemoteUsername": "DyfanJones",
+      "RemoteRepo": "noctua",
+      "RemoteRef": "master",
+      "RemoteSha": "23a4cfbf537407c7a1547fc13ba771ba2eb098e0",
       "Requirements": [
         "DBI",
         "R",
@@ -436,7 +487,17 @@
         "utils",
         "uuid"
       ],
-      "Hash": "c03d73125d695e80b35b4bb3eacf0358"
+      "Hash": "a48e1decdd027c44ea6b97b0fe0950cb"
+    },
+    "openssl": {
+      "Package": "openssl",
+      "Version": "2.2.2",
+      "Source": "Repository",
+      "Repository": "CRAN",
+      "Requirements": [
+        "askpass"
+      ],
+      "Hash": "d413e0fef796c9401a4419485f709ca1"
     },
     "openxlsx": {
       "Package": "openxlsx",
@@ -455,6 +516,178 @@
       ],
       "Hash": "14304e44a0f90fa2d0f905472333c561"
     },
+    "paws": {
+      "Package": "paws",
+      "Version": "0.7.0",
+      "Source": "Repository",
+      "Repository": "CRAN",
+      "Requirements": [
+        "paws.analytics",
+        "paws.application.integration",
+        "paws.common",
+        "paws.compute",
+        "paws.cost.management",
+        "paws.customer.engagement",
+        "paws.database",
+        "paws.developer.tools",
+        "paws.end.user.computing",
+        "paws.machine.learning",
+        "paws.management",
+        "paws.networking",
+        "paws.security.identity",
+        "paws.storage"
+      ],
+      "Hash": "e86280169e0edf73aeb255dc3291a78c"
+    },
+    "paws.analytics": {
+      "Package": "paws.analytics",
+      "Version": "0.7.0",
+      "Source": "Repository",
+      "Repository": "CRAN",
+      "Requirements": [
+        "paws.common"
+      ],
+      "Hash": "0b550ad3a3196182b3972d87f67ee52f"
+    },
+    "paws.application.integration": {
+      "Package": "paws.application.integration",
+      "Version": "0.7.0",
+      "Source": "Repository",
+      "Repository": "CRAN",
+      "Requirements": [
+        "paws.common"
+      ],
+      "Hash": "56caa9cc142939976c23d618de875fad"
+    },
+    "paws.common": {
+      "Package": "paws.common",
+      "Version": "0.7.7",
+      "Source": "Repository",
+      "Repository": "CRAN",
+      "Requirements": [
+        "Rcpp",
+        "base64enc",
+        "curl",
+        "digest",
+        "httr",
+        "jsonlite",
+        "methods",
+        "stats",
+        "utils",
+        "xml2"
+      ],
+      "Hash": "d184fea5f7f48426720b84f5b488380d"
+    },
+    "paws.compute": {
+      "Package": "paws.compute",
+      "Version": "0.7.0",
+      "Source": "Repository",
+      "Repository": "CRAN",
+      "Requirements": [
+        "paws.common"
+      ],
+      "Hash": "ff7b5df4fe6a395bc007bee9fe66e35b"
+    },
+    "paws.cost.management": {
+      "Package": "paws.cost.management",
+      "Version": "0.7.0",
+      "Source": "Repository",
+      "Repository": "CRAN",
+      "Requirements": [
+        "paws.common"
+      ],
+      "Hash": "ec6dc962be2e52a3bc80705453f36498"
+    },
+    "paws.customer.engagement": {
+      "Package": "paws.customer.engagement",
+      "Version": "0.7.0",
+      "Source": "Repository",
+      "Repository": "CRAN",
+      "Requirements": [
+        "paws.common"
+      ],
+      "Hash": "c54f1f22133b1c871bdf55eff0696cd4"
+    },
+    "paws.database": {
+      "Package": "paws.database",
+      "Version": "0.7.0",
+      "Source": "Repository",
+      "Repository": "CRAN",
+      "Requirements": [
+        "paws.common"
+      ],
+      "Hash": "60369b1a0313bb8f851fce55cf2628f7"
+    },
+    "paws.developer.tools": {
+      "Package": "paws.developer.tools",
+      "Version": "0.7.0",
+      "Source": "Repository",
+      "Repository": "CRAN",
+      "Requirements": [
+        "paws.common"
+      ],
+      "Hash": "1ce7155cae73833be217e21521c32e3e"
+    },
+    "paws.end.user.computing": {
+      "Package": "paws.end.user.computing",
+      "Version": "0.7.0",
+      "Source": "Repository",
+      "Repository": "CRAN",
+      "Requirements": [
+        "paws.common"
+      ],
+      "Hash": "186cf97ccd324024f711198947276e7a"
+    },
+    "paws.machine.learning": {
+      "Package": "paws.machine.learning",
+      "Version": "0.7.0",
+      "Source": "Repository",
+      "Repository": "CRAN",
+      "Requirements": [
+        "paws.common"
+      ],
+      "Hash": "c7f9d15e133abc4a5110a06f9b278bbd"
+    },
+    "paws.management": {
+      "Package": "paws.management",
+      "Version": "0.7.0",
+      "Source": "Repository",
+      "Repository": "CRAN",
+      "Requirements": [
+        "paws.common"
+      ],
+      "Hash": "825160604065040b1927448b4ff74ee5"
+    },
+    "paws.networking": {
+      "Package": "paws.networking",
+      "Version": "0.7.0",
+      "Source": "Repository",
+      "Repository": "CRAN",
+      "Requirements": [
+        "paws.common"
+      ],
+      "Hash": "9f797402420b714f197129ab3ebc0623"
+    },
+    "paws.security.identity": {
+      "Package": "paws.security.identity",
+      "Version": "0.7.0",
+      "Source": "Repository",
+      "Repository": "CRAN",
+      "Requirements": [
+        "paws.common"
+      ],
+      "Hash": "dabf1af10c69094cac1a431f3dc2eb1c"
+    },
+    "paws.storage": {
+      "Package": "paws.storage",
+      "Version": "0.7.0",
+      "Source": "Repository",
+      "Repository": "CRAN",
+      "Requirements": [
+        "paws.common"
+      ],
+      "Hash": "867ac96c9b97e47c23efbf97e809aed4"
+    },
     "pillar": {
       "Package": "pillar",
       "Version": "1.9.0",
@@ -496,7 +729,7 @@
       "Package": "progress",
       "Version": "1.2.3",
       "Source": "Repository",
-      "Repository": "RSPM",
+      "Repository": "CRAN",
       "Requirements": [
         "R",
         "R6",
@@ -610,6 +843,13 @@
       ],
       "Hash": "39e1144fd75428983dc3f63aa53dfa91"
     },
+    "sys": {
+      "Package": "sys",
+      "Version": "3.4.3",
+      "Source": "Repository",
+      "Repository": "CRAN",
+      "Hash": "de342ebfebdbf40477d0758d05426646"
+    },
     "tibble": {
       "Package": "tibble",
       "Version": "3.2.1",
@@ -670,17 +910,27 @@
       "Package": "utf8",
       "Version": "1.2.4",
       "Source": "Repository",
-      "Repository": "RSPM",
+      "Repository": "CRAN",
       "Requirements": [
         "R"
       ],
       "Hash": "62b65c52671e6665f803ff02954446e9"
     },
+    "uuid": {
+      "Package": "uuid",
+      "Version": "1.2-1",
+      "Source": "Repository",
+      "Repository": "CRAN",
+      "Requirements": [
+        "R"
+      ],
+      "Hash": "34e965e62a41fcafb1ca60e9b142085b"
+    },
     "vctrs": {
       "Package": "vctrs",
       "Version": "0.6.5",
       "Source": "Repository",
-      "Repository": "RSPM",
+      "Repository": "CRAN",
       "Requirements": [
         "R",
         "cli",
@@ -694,7 +944,7 @@
       "Package": "vroom",
       "Version": "1.6.5",
       "Source": "Repository",
-      "Repository": "RSPM",
+      "Repository": "CRAN",
       "Requirements": [
         "R",
         "bit64",
@@ -741,6 +991,19 @@
       ],
       "Hash": "8687398773806cfff9401a2feca96298"
     },
+    "xml2": {
+      "Package": "xml2",
+      "Version": "1.3.6",
+      "Source": "Repository",
+      "Repository": "CRAN",
+      "Requirements": [
+        "R",
+        "cli",
+        "methods",
+        "rlang"
+      ],
+      "Hash": "1d0336142f4cd25d8d23cd3ba7a8fb61"
+    },
     "yaml": {
       "Package": "yaml",
       "Version": "2.3.10",
diff --git a/renv/profiles/reporting/renv.lock b/renv/profiles/reporting/renv.lock
index cf254a2..ce5304a 100644
--- a/renv/profiles/reporting/renv.lock
+++ b/renv/profiles/reporting/renv.lock
@@ -65,7 +65,7 @@
     },
     "Matrix": {
       "Package": "Matrix",
-      "Version": "1.7-1",
+      "Version": "1.6-5",
       "Source": "Repository",
       "Repository": "CRAN",
       "Requirements": [
@@ -78,7 +78,7 @@
         "stats",
         "utils"
       ],
-      "Hash": "5122bb14d8736372411f955e1b16bc8a"
+      "Hash": "8c7115cd3a0e048bda2a7cd110549f7a"
     },
     "R6": {
       "Package": "R6",
@@ -111,6 +111,20 @@
       ],
       "Hash": "6b868847b365672d6c1677b1608da9ed"
     },
+    "RcppArmadillo": {
+      "Package": "RcppArmadillo",
+      "Version": "14.2.2-1",
+      "Source": "Repository",
+      "Repository": "CRAN",
+      "Requirements": [
+        "R",
+        "Rcpp",
+        "methods",
+        "stats",
+        "utils"
+      ],
+      "Hash": "9da7c242d94a8419d045f6b3a64b9765"
+    },
     "askpass": {
       "Package": "askpass",
       "Version": "1.2.1",
@@ -930,7 +944,7 @@
     },
     "lattice": {
       "Package": "lattice",
-      "Version": "0.22-6",
+      "Version": "0.22-5",
       "Source": "Repository",
       "Repository": "CRAN",
       "Requirements": [
@@ -941,7 +955,7 @@
         "stats",
         "utils"
       ],
-      "Hash": "cc5ac1ba4c238c7ca9fa6a87ca11a7e2"
+      "Hash": "7c5e89f04e72d6611c77451f6331a091"
     },
     "lazyeval": {
       "Package": "lazyeval",
@@ -1098,7 +1112,7 @@
     },
     "nlme": {
       "Package": "nlme",
-      "Version": "3.1-166",
+      "Version": "3.1-165",
       "Source": "Repository",
       "Repository": "CRAN",
       "Requirements": [
@@ -1108,7 +1122,7 @@
         "stats",
         "utils"
       ],
-      "Hash": "ccbb8846be320b627e6aa2b4616a2ded"
+      "Hash": "2769a88be217841b1f33ed469675c3cc"
     },
     "numDeriv": {
       "Package": "numDeriv",
@@ -1698,7 +1712,7 @@
     },
     "terra": {
       "Package": "terra",
-      "Version": "1.7-83",
+      "Version": "1.8-5",
       "Source": "Repository",
       "Repository": "CRAN",
       "Requirements": [
@@ -1706,7 +1720,7 @@
         "Rcpp",
         "methods"
       ],
-      "Hash": "fbeffe988419d292225a57cf9c284802"
+      "Hash": "6e3f2c53b58161327fe5787fe1a63d02"
     },
     "tibble": {
       "Package": "tibble",