Dominion Akinrotimi
Back to Projects
Pythonscikit-learnClassificationModel evaluation

Predicting Delivery Delays for SwiftChain

The problem: a logistics company wants to know at order time whether a delivery will arrive early, on time or late, so it can warn customers before they complain.

What I built: a model trained on 15,549 orders that uses only what's known when the order is placed, compared fairly against a simple baseline.

View the code on GitHub

Results

Bar chart of macro F1: models score about 0.47 against 0.24 for the baseline

Macro F1 on 3,110 held-out orders. Each outcome counts equally.

ModelAccuracyMacro F1
Always predict "late" (baseline)57.7%0.244
Logistic Regression53.4%0.469
Random Forest54.2%0.462
Hist Gradient Boosting52.8%0.477

Accuracy is misleading here. 58% of orders are late, so always guessing "late" scores 58% while never finding an early or on-time order. On macro F1 the models roughly double the baseline.

Where it's useful: when the model flags an order as late, it's right 87% of the time, which is precise enough to trigger a proactive delay message. It also catches 86% of early arrivals. On-time orders remain hard to tell apart.

An honest correction

My first version reported 71.7% accuracy. That number came from oversampling (SMOTE) the whole dataset before splitting it, so about 4 in 10 test rows were synthetic copies built from training rows. It also used order and customer IDs as features. This rebuild balances classes inside training only, drops IDs and the shipping date (known only after the fact), and compares every model with a baseline.

What drives delays

Shipping mode carries almost all of the signal. Shuffling it drops macro F1 by 0.17, and no other feature drops it by more than 0.01. Better predictions would need carrier, warehouse and route data.

Confusion matrix of early, on-time and late predictions

Confusion matrix for the best model.

Have data you cannot make sense of yet?

I turn raw data into dashboards, reports and decisions your team can act on.