DS2021_second

2 years, 2 months ago

Second semester project for Decision Systems 2021/2022 Course

This is the second project for students enrolled in the Decision System 2021/2022 course at the Faculty of Mathematics, Informatics, and Mechanics at the University of Warsaw.

Overview

Your task is to construct a model for predicting sales of products offered by the FitFood company at their FitBoxy locations in Poland, during the COVID-19 pandemic period.

More detailed competition rules are given in Terms and Conditions.

The description of the data and evaluation metric is in the Task description section.

The submission system will open on Monday, December 20.

Terms & Conditions

Participants of the challenge are obliged to follow the competition rules:

This challenge is organized by Andrzej Janusz (the Organizer) for students enrolled in the Decision System 2021/2022 course at the Faculty of Mathematics, Informatics, and Mechanics at the University of Warsaw.
The provided data sets are the property of the Organizer and the KnowledgePit platform. It is forbidden to share or redistribute provided data sets to any third party without explicit consent from the Organizer.
Participants can work individually or as a team consisting of maximally two persons. The teams need to be formed at the beginning of the challenge. Participants cannot change their teams.
Each team has a limited number of submissions - the limit is set to 100.
The number of submissions per day is limited to 5.
Participants can use data that was made available in the challenge - using any external resources is possible only after receiving explicit consent from the Organizer. Queries regarding the external resources need to be issued through the competition forum.
It is strictly forbidden to hack the provided data or to exploit any unfair data leak that can improve the solution score. All attempts at making predictions for any test instance using information extracted from other test instances will result in disqualification.
The deadline for submitting the solutions is January 23, 2022 (23:59 GMT). Late submissions will not be accepted.
Each team is obliged to provide a short report describing their final solution. The report must contain information such as the name of the team, the names of all team members, and a brief overview of the used approach. The description should explain all data preprocessing steps and model construction steps. It should be submitted in the KnowledgePit submission system by January 23, 2022 (23:59 GMT).
By enrolling in this competition, you grant the Organizer the right to process your submissions and reports for the purpose of evaluation and post-competition research.
The final project score will depend on the quality of the solution (the score obtained in the final evaluation), and on the quality of the submitted report.

Enroll

Please log in to the system!

Task description

Provided data sets describe a short-term sales history of products at various points of sales (PoS). The target attribute target_sales indicates the number of sold products of a given type in the following 7 day period. The split into the training and test cases is such that the training data corresponds to the period between 2019-01-01 and 2020-07-01 (pre-pandemic and the first lock-down). The test data set covers the one year of pandemic after the training period.

The data tables are provided as two CSV files with the coma ',' separator sign. They can be downloaded after the enrollment for the challenge. Both files (training and test sets) have exactly the same format but all the values from the target_sales column in the test set are missing.

The evaluation metric will be MAE. During the challenge, your solutions will be evaluated on a small fraction of the test set, and your best preliminary MAE score will be displayed on the public Leaderboard.

The submission format: the solutions need to be submitted as text files with predictions. The file should have exactly the same number of rows as the test data table (not counting the header, which should be omitted). In each row, it should contain exactly one number expressing the predicted sales.

Data files

In order to download competition files you need to be enrolled.

Forum

This forum is for all users to discuss matters related to the competition. Good manners apply!

There is no topics in this competition.

Final results

Rank	Team Name	Is Report	Preliminary Score	Final Score	Submissions
1	harMLess	True	1.9462	1.957400	20
2	Zerglings	True	1.9505	1.994500	12
3	NazwaTymaczasowoTymczasowa	True	1.9536	1.998300	53
4	żuk_w_pudełku	True	2.0203	2.021900	13
5	baseline	True	2.0406	2.022900	1
6	jw_hl	True	2.0468	2.026000	6
7	Alek	True	2.0194	2.040600	16
8	Czarne wrony	True	2.0075	2.044600	11
9	SG	True	2.0844	2.049600	3
10	WszystkoJestLiniowe	True	1.9771	2.057700	8
11	LK	True	2.0635	2.075000	5
12	Lagrange	True	2.0981	2.075700	5
13	Tomato	True	2.3684	2.360800	9
14	Zespół R	True	2.4680	2.400800	11