Delivery Drivers

A delivery optimization project using causal inference and logistic optimization

Project details

Table of contents

• Introduction
• Objective
• Data
• Requirements
• Screenshots
• Notebooks
• Scripts
• Test
• Authors

Introduction

Our client for this week's challenge is Gokada - the largest last-mile delivery service in Nigeria. Gokada works are partnered with motorbike owners and drivers to deliver parcels across Lagos, Nigeria. One key issue Gokada has faced as it expands its service is the sub-optimal placement of pilots and clients who want to use Gokada to send their parcels. This has led to a high number of unfulfilled delivery requests.

Therefore, Gokada is asking 10 Academy trainees, to work on its data to help it understand the primary causes of unfulfilled requests as well as come up with solutions that recommend drivers' locations that increase the fraction of complete orders. Since drivers are paid based on the number of requests they accept, your solution will help Gokada's business grow both in terms of client satisfaction and increased business.

We will be using causal inference and logistic optimization models to achieve the objective mentioned above.

Objective

This objective of this project is very straightforward: use causal inference and logistic optimization to increase the number of fulfilled deliveries, decrease unfulfilled deliveries, increase customer satisfaction and understand the primary cause of unfulfilled requests as well as come up with solutions that recommend drivers' locations that increase the fraction of complete orders.

Data

As mentioned above our client for this week is Gokada. The data was directly obtained from their company which they have been collecting over their years of delivering parcels to customers and is not shared to the public or third parties.

There were two data sets that were provided. The first dataset contains information regarding the delivery trip and its attributes while the second contains information related to the drivers, the actions they took, and their location.

Requirements

Pip

Python 3.5 or above

You can find the full list of requirements in the requirements.txt file

Screenshots

Several screenshots related to the project could be found here, in the screenshots folder.

Notebooks

All the notebooks that are used in this project including EDA, data cleaning and summarization along with some machine learning model generations are found here in the Notebooks folder.

Scripts

All the custom scripts, modules, default parameters and values used for this project used will be found here, in the scripts folder.

Tests

All the unit and integration tests are found here in the tests folder.

Authors

👤 Fisseha Estifanos

• Email, GitHub, LinkedIn, Twitter

Show us your support

Give us a ⭐ if you like this project, and also feel free to contact us at any moment.