# Evaluation This competition evaluates submissions on the percentage of correct predictions. For each task, you should predict exactly 2 outputs for every test input grid contained in the task. (Tasks can have more than one test input that needs a predicted output.) Each task test output has one ground truth. For a given task output, any of the 2 predicted outputs matches the ground truth exactly, you score 1 for that task test output, otherwise 0. The final score is the sum averaged of the highest score per task output divided by the total number of task test outputs. ### Submission File The submission file for this competition must be a json named submission.json. For each task output in the evaluation set, you should make exactly 2 predictions (attempt_1, attempt_2). The structure of predictions is shown below. Most tasks only have a single output (a single dictionary enclosed in a list), although some tasks have multiple outputs that must be predicted. These should contain two dictionaries of predictions enclosed in a list, as is shown by the example below. When a task has multiple test outputs that need to be predicted (e.g., task 12997ef3 below), they must be in the same order as the corresponding test inputs. \`\`\`json { "00576224": [{"attempt_1": [[0, 0], [0, 0]], "attempt_2": [[0, 0], [0, 0]]}, "009d5c81": [{"attempt_1": [[0, 0], [0, 0]], "attempt_2": [[0, 0], [0, 0]]}, "12997ef3": [{"attempt_1": [[0, 0], [0, 0]], "attempt_2": [[0, 0], [0, 0]]}, {"attempt_1": [[0, 0], [0, 0]], "attempt_2": [[0, 0], [0, 0]]}], ... } \`\`\` # Code Requirements ### This is a Code Competition Submissions to this competition must be made through Notebooks. In order for the "Submit to Competition" button to be active after a commit, the following conditions must be met: - CPU Notebook <= 12 hours run-time - GPU Notebook <= 12 hours run-time - No internet access enabled - External data, freely & publicly available, is allowed, including pre-trained models - Submission file must be named submission.json

# Evaluation This competition evaluates submissions on the percentage of correct predictions. For each task, you should predict exactly 2 outputs for every test input grid contained in the task. (Tasks can have more than one test input that needs a predicted output.) Each task test output has one ground truth. For a given task output, any of the 2 predicted outputs matches the ground truth exactly, you score 1 for that task test output, otherwise 0. The final score is the sum averaged of the highest score per task output divided by the total number of task test outputs. ### Submission File The submission file for this competition must be a json named submission.json. For each task output in the evaluation set, you should make exactly 2 predictions (attempt_1, attempt_2). The structure of predictions is shown below. Most tasks only have a single output (a single dictionary enclosed in a list), although some tasks have multiple outputs that must be predicted. These should contain two dictionaries of predictions enclosed in a list, as is shown by the example below. When a task has multiple test outputs that need to be predicted (e.g., task 12997ef3 below), they must be in the same order as the corresponding test inputs. \`\`\`json { "00576224": [{"attempt_1": [[0, 0], [0, 0]], "attempt_2": [[0, 0], [0, 0]]}, "009d5c81": [{"attempt_1": [[0, 0], [0, 0]], "attempt_2": [[0, 0], [0, 0]]}, "12997ef3": [{"attempt_1": [[0, 0], [0, 0]], "attempt_2": [[0, 0], [0, 0]]}, {"attempt_1": [[0, 0], [0, 0]], "attempt_2": [[0, 0], [0, 0]]}], ... } \`\`\` # Code Requirements ### This is a Code Competition Submissions to this competition must be made through Notebooks. In order for the "Submit to Competition" button to be active after a commit, the following conditions must be met: - CPU Notebook <= 12 hours run-time - GPU Notebook <= 12 hours run-time - No internet access enabled - External data, freely & publicly available, is allowed, including pre-trained models - Submission file must be named submission.json

# Evaluation This competition evaluates submissions on the percentage of correct predictions. For each task, you should predict exactly 2 outputs for every test input grid contained in the task. (Tasks can have more than one test input that needs a predicted output.) Each task test output has one ground truth. For a given task output, any of the 2 predicted outputs matches the ground truth exactly, you score 1 for that task test output, otherwise 0. The final score is the sum averaged of the highest score per task output divided by the total number of task test outputs. ### Submission File The submission file for this competition must be a json named submission.json. For each task output in the evaluation set, you should make exactly 2 predictions (attempt_1, attempt_2). The structure of predictions is shown below. Most tasks only have a single output (a single dictionary enclosed in a list), although some tasks have multiple outputs that must be predicted. These should contain two dictionaries of predictions enclosed in a list, as is shown by the example below. When a task has multiple test outputs that need to be predicted (e.g., task 12997ef3 below), they must be in the same order as the corresponding test inputs. \`\`\`json { "00576224": [{"attempt_1": [[0, 0], [0, 0]], "attempt_2": [[0, 0], [0, 0]]}, "009d5c81": [{"attempt_1": [[0, 0], [0, 0]], "attempt_2": [[0, 0], [0, 0]]}, "12997ef3": [{"attempt_1": [[0, 0], [0, 0]], "attempt_2": [[0, 0], [0, 0]]}, {"attempt_1": [[0, 0], [0, 0]], "attempt_2": [[0, 0], [0, 0]]}], ... } \`\`\` # Code Requirements ### This is a Code Competition Submissions to this competition must be made through Notebooks. In order for the "Submit to Competition" button to be active after a commit, the following conditions must be met: - CPU Notebook <= 12 hours run-time - GPU Notebook <= 12 hours run-time - No internet access enabled - External data, freely & publicly available, is allowed, including pre-trained models - Submission file must be named submission.json

# Walmart Store Sales Dataset ## Overview The Walmart Store Sales Dataset is a comprehensive collection of historical sales data from Walmart, one of the largest retail chains in the world. This dataset is ideal for time series analysis, sales forecasting, and data-driven decision-making. With over **1.6 million rows** of detailed sales information, it provides a rich resource for exploring various aspects of retail sales, trends, and patterns. ## Dataset Description The dataset contains the following features: - **Store**: The store number. - **Date**: The week of the year when the sales were recorded. - **Weekly_Sales**: The total sales for the given store in that particular week. - **Holiday_Flag**: A binary flag indicating whether the week includes a major holiday (1 for holiday week, 0 otherwise). - **Temperature**: The average temperature in the region during that week. - **Fuel_Price**: The cost of fuel in the region during that week. - **CPI (Consumer Price Index)**: The measure of the average change over time in the prices paid by urban consumers for goods and services. - **Unemployment**: The unemployment rate in the region during that week. ## Applications This dataset can be used for various purposes, including but not limited to: - **Sales Forecasting**: Predict future sales based on historical data. - **Trend Analysis**: Identify patterns and trends in sales over time. - **Impact Analysis**: Assess the impact of external factors like holidays, fuel prices, and unemployment rates on sales. - **Retail Strategy Development**: Develop strategies for inventory management, pricing, and promotions based on insights derived from the data. ## Dataset Size - **Total Rows**: 1,600,000+ - **Total Columns**: 8 ## File Format The dataset is available in **CSV** format, making it easy to import into various data analysis and machine learning tools. ## Usage To use this dataset for sales forecasting, you can start by loading the data into a Python or R environment. From there, you can clean and preprocess the data, create time series models, and analyze the effects of different variables on sales. ## License Please refer to the dataset's licensing terms before use. ## Contribution We encourage contributions from the community to improve the dataset and share insights. If you have any suggestions, improvements, or findings, feel free to contribute! ## Acknowledgments This dataset is provided by Walmart for educational and research purposes. We acknowledge their contribution to the data science community. --- Feel free to reach out with any questions or to share your findings!