This is a private hackathon whose primary purpose is for the members of the EXPLORE Data Science Academy to apply what they have learnt. If you are part of EDSA contact your mentor for the secret code.

Logistics in Sub-Saharan Africa increases the cost of manufactured goods by up to 320%; while in Europe, it only accounts for up to 90% of the manufacturing cost.

Economies are better when logistics is efficient and affordable.

Sendy, in partnership with insight2impact facility, is hosting a Zindi challenge to predict the estimated time of delivery of orders, from the point of driver pickup to the point of arrival at final destination.

The solution will help Sendy enhance customer communication and improve the reliability of its service; which will ultimately improve customer experience. In addition, the solution will enable Sendy to realise cost savings, and ultimately reduce the cost of doing business, through improved resource management and planning for order scheduling.

Sendy helps men and women behind every type of business to trade easily, deliver more competitively, and build extraordinary businesses.

“We believe in them; we believe that logistics should be an enabler for them to achieve their goals, rather than a hindrance. We believe that everyone should be able to participate and thrive in the economy and that no small business should be left out because the cost of logistics is either too high or inaccessible.”

Data is a critical component in helping Sendy to build more efficient, affordable and accessible solutions. Given the details of a Sendy order, can we use historic data to predict an accurate time for the arrival of the rider at the destination of a package? In this competition, we’re challenging you to build a model that predicts an accurate delivery time, from picking up a package to arriving at the final destination. An accurate arrival time prediction will help all businesses to improve their logistics and communicate an accurate time to their customers.

This competition is being hosted by Sendy.

About EDSA (explore-datascience.net):

EDSA is an academy which teaches and uses data science to solve real world problems. Founded by three actuaries who discovered that their passion for pedagogy could address a fundamental skills shortage, EDSA has grown in leaps and bounds; going from a single campus within Cape Town in 2017, to three physical campuses across South Africa, as well as an ever-growing online presence.

In teaching aspects of data analysis and machine learning, EDSA aims to support and use local data platforms like Zindi; exposing students to a vibrant community seeking to make a difference with data, while enabling them to practice and apply their skills within real world scenarios. The Sendy Logistics Challenge is an example of such a real world problem for which regression techniques in particular can be applied, and makes up a learning component for the student’s academic activities this year.

About Sendy(sendyit.com):

Sendy is a business-to-business platform established in 2014, to enable businesses of all types and sizes to transport goods more efficiently across East Africa.

The company is headquartered in Kenya with a team of more than 100 staff, focused on building practical solutions for Africa’s dynamic transportation needs, from developing apps and web solutions, to providing dedicated support for goods on the move.

Currently operating in Kenya and Uganda, Sendy is expanding to Nigeria and Tanzania, to enable thousands more businesses to move volumes of goods easily, anywhere, at any time. Sendy aggregates a pool of delivery options from 28 ton, 14 ton, 5 ton trucks to pick up trucks, vans and motorcycles.

“At Sendy, we’re on a mission to change the lives of everyone we touch; from patients who rely on regular medicine at the local pharmacy to farmers who urgently need to move their produce to silos, we are offering a service that African companies can depend on. We are building a platform to tackle logistic challenges that business across Africa face on a day to day basis.”

This is a private hackathon whose primary purpose is for the members of the EXPLORE Data Science Academy to apply what they have learnt. If you are part of EDSA contact your mentor for the secret code.

You may use only the datasets provided for this competition. Your solution must use machine learning with an emphasis on regression analysis and related techniques.

Participation within this competition occurs on a team basis for full-time students, and on an individual basis for part-time students. Students are to consult their Predict instructions for further details around team-work. You must adhere to the rules associated with teaming up.

Multiple accounts per user are not allowed. Collaboration across individuals not in the same team is not allowed, and collaboration between different teams is not allowed.

Code must not be shared privately, except amongst individuals within the same team.

The solution must use publicly-available, open-source packages only.

Maximum 20 solutions submitted per day. Your highest-scoring solution will be the one by which you are judged.

Note that there are Public and Private Leaderboards. The Public Leaderboard excludes approximately 50% of the test dataset. While the competition is open, the Public Leaderboard will rank the submitted solutions by the accuracy score they achieve. Upon close of the competition, the Private Leaderboard, which covers 100% of the test dataset, will be made public and will constitute the final ranking for the competition.

The data used in this competition is the sole property of Zindi and the competition host. You may not transmit, duplicate, publish, redistribute or otherwise provide or make available any competition data to any party not participating in the Competition (this includes uploading the data to any public site such as Kaggle or GitHub). You may upload, store and work with the data on any cloud platform such as Google Colab, AWS or similar, as long as 1) the data remains private and 2) doing so does not contravene Zindi’s rules of use.

Refer to the FAQs and Terms of Use for additional rules that may apply to this competition.

You acknowledge and agree that Zindi may, without any obligation to do so, remove or disqualify an individual, team, or account if Zindi believes that such individual, team, or account is in violation of these Rules.

We reserve the right to modify these rules at any time as necessary.

The error metric for this competition is the Root Mean Squared Error

For every row in the dataset, submission files should contain 2 columns: order_id and Time from Pickup to Arrival (Predicted time in seconds between arrival and Pickup).

Your submission file should look like this:

Order_No                Time from Pickup to Arrival
Order_No_19248          197
Order_No_12736          7533
Order_No_768            768

This competition closes on 7 September 2020.

Final submissions are due on 02 June (Full-time/On-Premises Cohort) and 7 September (Part-time/Online Cohort) respectively.