diff --git a/DIRECTORY.md b/DIRECTORY.md
index 28114a88ae3..8c8f247104b 100644
--- a/DIRECTORY.md
+++ b/DIRECTORY.md
@@ -159,6 +159,7 @@
       * [Hinge Loss](https://github.com/TheAlgorithms/Rust/blob/master/src/machine_learning/loss_function/hinge_loss.rs)
       * [Huber Loss](https://github.com/TheAlgorithms/Rust/blob/master/src/machine_learning/loss_function/huber_loss.rs)
       * [Kl Divergence Loss](https://github.com/TheAlgorithms/Rust/blob/master/src/machine_learning/loss_function/kl_divergence_loss.rs)
+      * [Marginal Ranking Loss](https://github.com/TheAlgorithms/Rust/blob/master/src/machine_learning/loss_function/average_margin_ranking_loss.rs)
       * [Mean Absolute Error Loss](https://github.com/TheAlgorithms/Rust/blob/master/src/machine_learning/loss_function/mean_absolute_error_loss.rs)
       * [Mean Squared Error Loss](https://github.com/TheAlgorithms/Rust/blob/master/src/machine_learning/loss_function/mean_squared_error_loss.rs)
       * [Negative Log Likelihood](https://github.com/TheAlgorithms/Rust/blob/master/src/machine_learning/loss_function/negative_log_likelihood.rs)
diff --git a/src/machine_learning/loss_function/average_margin_ranking_loss.rs b/src/machine_learning/loss_function/average_margin_ranking_loss.rs
new file mode 100644
index 00000000000..505bf2a94a7
--- /dev/null
+++ b/src/machine_learning/loss_function/average_margin_ranking_loss.rs
@@ -0,0 +1,113 @@
+/// Marginal Ranking
+///
+/// The 'average_margin_ranking_loss' function calculates the Margin Ranking loss, which is a
+/// loss function used for ranking problems in machine learning.
+///
+/// ## Formula
+///
+/// For a pair of values `x_first` and `x_second`, `margin`, and `y_true`,
+/// the Margin Ranking loss is calculated as:
+///
+///  - loss = `max(0, -y_true * (x_first - x_second) + margin)`.
+///
+/// It returns the average loss by dividing the `total_loss` by total no. of
+/// elements.
+///
+/// Pytorch implementation:
+/// https://pytorch.org/docs/stable/generated/torch.nn.MarginRankingLoss.html
+/// https://gombru.github.io/2019/04/03/ranking_loss/
+/// https://vinija.ai/concepts/loss/#pairwise-ranking-loss
+///
+
+pub fn average_margin_ranking_loss(
+    x_first: &[f64],
+    x_second: &[f64],
+    margin: f64,
+    y_true: f64,
+) -> Result<f64, MarginalRankingLossError> {
+    check_input(x_first, x_second, margin, y_true)?;
+
+    let total_loss: f64 = x_first
+        .iter()
+        .zip(x_second.iter())
+        .map(|(f, s)| (margin - y_true * (f - s)).max(0.0))
+        .sum();
+    Ok(total_loss / (x_first.len() as f64))
+}
+
+fn check_input(
+    x_first: &[f64],
+    x_second: &[f64],
+    margin: f64,
+    y_true: f64,
+) -> Result<(), MarginalRankingLossError> {
+    if x_first.len() != x_second.len() {
+        return Err(MarginalRankingLossError::InputsHaveDifferentLength);
+    }
+    if x_first.is_empty() {
+        return Err(MarginalRankingLossError::EmptyInputs);
+    }
+    if margin < 0.0 {
+        return Err(MarginalRankingLossError::NegativeMargin);
+    }
+    if y_true != 1.0 && y_true != -1.0 {
+        return Err(MarginalRankingLossError::InvalidValues);
+    }
+
+    Ok(())
+}
+
+#[derive(Debug, PartialEq, Eq)]
+pub enum MarginalRankingLossError {
+    InputsHaveDifferentLength,
+    EmptyInputs,
+    InvalidValues,
+    NegativeMargin,
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    macro_rules! test_with_wrong_inputs {
+        ($($name:ident: $inputs:expr,)*) => {
+            $(
+                #[test]
+                fn $name() {
+                    let (vec_a, vec_b, margin, y_true, expected) = $inputs;
+                    assert_eq!(average_margin_ranking_loss(&vec_a, &vec_b, margin, y_true), expected);
+                    assert_eq!(average_margin_ranking_loss(&vec_b, &vec_a, margin, y_true), expected);
+                }
+            )*
+        }
+    }
+
+    test_with_wrong_inputs! {
+        invalid_length0: (vec![1.0, 2.0, 3.0], vec![2.0, 3.0], 1.0, 1.0, Err(MarginalRankingLossError::InputsHaveDifferentLength)),
+        invalid_length1: (vec![1.0, 2.0], vec![2.0, 3.0, 4.0], 1.0, 1.0, Err(MarginalRankingLossError::InputsHaveDifferentLength)),
+        invalid_length2: (vec![], vec![1.0, 2.0, 3.0], 1.0, 1.0, Err(MarginalRankingLossError::InputsHaveDifferentLength)),
+        invalid_length3: (vec![1.0, 2.0, 3.0], vec![], 1.0, 1.0, Err(MarginalRankingLossError::InputsHaveDifferentLength)),
+        invalid_values: (vec![1.0, 2.0, 3.0], vec![2.0, 3.0, 4.0], -1.0, 1.0, Err(MarginalRankingLossError::NegativeMargin)),
+        invalid_y_true: (vec![1.0, 2.0, 3.0], vec![2.0, 3.0, 4.0], 1.0, 2.0, Err(MarginalRankingLossError::InvalidValues)),
+        empty_inputs: (vec![], vec![], 1.0, 1.0, Err(MarginalRankingLossError::EmptyInputs)),
+    }
+
+    macro_rules! test_average_margin_ranking_loss {
+        ($($name:ident: $inputs:expr,)*) => {
+            $(
+                #[test]
+                fn $name() {
+                    let (x_first, x_second, margin, y_true, expected) = $inputs;
+                    assert_eq!(average_margin_ranking_loss(&x_first, &x_second, margin, y_true), Ok(expected));
+                }
+            )*
+        }
+    }
+
+    test_average_margin_ranking_loss! {
+        set_0: (vec![1.0, 2.0, 3.0], vec![2.0, 3.0, 4.0], 1.0, -1.0, 0.0),
+        set_1: (vec![1.0, 2.0, 3.0], vec![2.0, 3.0, 4.0], 1.0, 1.0, 2.0),
+        set_2: (vec![1.0, 2.0, 3.0], vec![1.0, 2.0, 3.0], 0.0, 1.0, 0.0),
+        set_3: (vec![4.0, 5.0, 6.0], vec![1.0, 2.0, 3.0], 1.0, -1.0, 4.0),
+    }
+}
diff --git a/src/machine_learning/loss_function/mod.rs b/src/machine_learning/loss_function/mod.rs
index 0637d63e1ef..95686eb8c20 100644
--- a/src/machine_learning/loss_function/mod.rs
+++ b/src/machine_learning/loss_function/mod.rs
@@ -1,3 +1,4 @@
+mod average_margin_ranking_loss;
 mod hinge_loss;
 mod huber_loss;
 mod kl_divergence_loss;
@@ -5,6 +6,7 @@ mod mean_absolute_error_loss;
 mod mean_squared_error_loss;
 mod negative_log_likelihood;
 
+pub use self::average_margin_ranking_loss::average_margin_ranking_loss;
 pub use self::hinge_loss::hng_loss;
 pub use self::huber_loss::huber_loss;
 pub use self::kl_divergence_loss::kld_loss;
diff --git a/src/machine_learning/mod.rs b/src/machine_learning/mod.rs
index c9344a508ef..c77fd65116b 100644
--- a/src/machine_learning/mod.rs
+++ b/src/machine_learning/mod.rs
@@ -7,6 +7,7 @@ mod optimization;
 pub use self::cholesky::cholesky;
 pub use self::k_means::k_means;
 pub use self::linear_regression::linear_regression;
+pub use self::loss_function::average_margin_ranking_loss;
 pub use self::loss_function::hng_loss;
 pub use self::loss_function::huber_loss;
 pub use self::loss_function::kld_loss;