{"success":true,"data":{"author":"Dingdong Inc.","bucketAccessType":"public","bucketName":"Dingdong-Inc/FreshRetailNet-50K","bucketPrefix":"","category":"Machine Learning & AI","cloudProvider":"huggingface","createdAt":"2026-11-14T14:15:20.292Z","description":"FreshRetailNet-50K, described by its authors as the first large-scale benchmark for censored demand estimation in fresh retail. It contains 50,000 store-product time series covering 90 days of detailed hourly sales from 898 stores in 18 major cities and 865 perishable SKUs, with stockout event annotations; about 20% of the data are organically occurring stockouts, so observed sales understate true demand. Rows carry encoded city, store, management group, three-level category and product ids, the date, normalised daily sale amount, hourly sales and hourly stock status, and covariates: discount rate, holiday and activity flags, precipitation, average temperature, humidity and wind level. Listing data/ (measured 2026-11-14) shows train.parquet (about 106 MB) and eval.parquet (about 8 MB). Uses include latent demand recovery under stockouts, demand forecasting for perishable goods, inventory and replenishment optimisation and time series imputation. Load with Hugging Face datasets or pandas; the GitHub repository has the baseline pipeline. Licensed CC BY 4.0 per the card; cite the FreshRetailNet-50K technical report.","displayTitle":"FreshRetailNet-50K: Fresh Retail Demand with Stockout Annotations","id":"18a2fca8-23e8-5226-a98c-d021e8b29691","license":"CC-BY-4.0","licenseEvidenceUrl":"https://huggingface.co/datasets/Dingdong-Inc/FreshRetailNet-50K","objectCountEstimate":5,"probeStatus":"ok","referenceUrl":"https://arxiv.org/abs/2505.16319","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"Dingdong-Inc/FreshRetailNet-50K\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"Dingdong-Inc/FreshRetailNet-50K\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=Dingdong-Inc, license:cc-by-4.0, size_categories:1M<n<10M, downloads=7999"],"format":"mixed","generatedAt":"2026-11-14T14:15:33.004Z","layout":{"example":"data/eval.parquet","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"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","encoding":"hex","key":"data/eval.parquet","truncatedAt":512}],"sampleObjects":["data/eval.parquet","data/train.parquet"],"sidecars":[{"bytes":"---\nlanguage:\n- en\nlicense: cc-by-4.0\ntask_categories:\n- time-series-forecasting\ntags:\n- fresh-retail\n- censored-demand\n- hourly-stock-status\nsize_categories:\n- 1M<n<10M\npretty_name: FreshRetailNet-50K\nconfigs:\n- config_name: default\n  data_files:\n  - split: train\n    path: data/train.parquet\n  - split: eval\n    path: data/eval.parquet\n---\n\n# FreshRetailNet-50K\n\n## Dataset Overview\nFreshRetailNet-50K is the first large-scale benchmark for censored demand estimation in the fresh retail domain, **incorporating approximately 20% organically occurring stockout data**. It comprises 50,000 store-product 90-day time series of detailed hourly sales data from 898 stores in 18 major cities, encompassing 865 perishable SKUs with meticulous stockout event annotations. The hourly stock status records unique to this dataset, combined with rich contextual covariates including promotional discounts, precipitation, and other temporal features, enable innovative research beyond existing solutions.\n\n- [Technical Report](https://arxiv.org/abs/2505.16319) - Discover the methodology and technical details behind FreshRetailNet-50K.\n- [Github Repo](https://github.com/Dingdong-Inc/frn-50k-baseline) - Access the complete pipeline used to train and evaluate.\n\nThis dataset is ready for commercial/non-commercial use.\n\n\n## Data Fields\n|Field|Type|Description|\n|:---|:---|:---|\n|city_id|int64|The encoded city id|\n|store_id|int64|The encoded store id|\n|management_group_id|int64|The encoded management group id|\n|first_category_id|int64|The encoded first category id|\n|second_category_id|int64|The encoded second category id|\n|third_category_id|int64|The encoded third category id|\n|product_id|int64|The encoded product id|\n|dt|string|The date|\n|sale_amount|float64|The daily sales quantity after global normalization (Multiplied by a specific coefficient)|\n|hours_sale|Sequence(float64)|The hourly sales quantity after global normalization (Multiplied by a specific coefficient)|\n|stock_hour6_22_cnt|int32|The number of out-of-stock hours between 6:00 and 22:00|\n|hours_stock_status|Sequence(int32)|The hourly out-of-stock status|\n|discount|float64|The discount rate (1.0 means no discount, 0.9 means 10% off)|\n|holiday_flag|int32|Holiday indicator|\n|activity_flag|int32|Activity indicator|\n|precpt|float64|The total precipitation|\n|avg_temperature|float64|The average temperature|\n|avg_humidity|float64|The average humidity|\n|avg_wind_level|float64|The average wind force|\n\n### Hierarchical structure\n- **warehouse**: city_id > store_id\n- **product category**: management_group_id > first_category_id > second_category_id > third_category_id > product_id\n\n\n\n## How to use it\n\nYou can load the dataset with the following lines of code.\n\n```python\nfrom datasets import load_dataset\ndataset = load_dataset(\"Dingdong-Inc/FreshRetailNet-50K\")\nprint(dataset)\n```\n```text\nDatasetDict({\n    train: Dataset({\n        features: ['city_id', 'store_id', 'management_group_id', 'first_category_id', 'second_category_id', 'third_category_id', 'product_id', 'dt', 'sale_amount', 'hours_sale', 'stock_hour6_22_cnt', 'hours_stock_status', 'discount', 'holiday_flag', 'activity_flag', 'precpt', 'avg_temperature', 'avg_humidity', 'avg_wind_level'],\n        num_rows: 4500000\n    })\n    eval: Dataset({\n        features: ['city_id', 'store_id', 'management_group_id', 'first_category_id', 'second_category_id', 'third_category_id', 'product_id', 'dt', 'sale_amount', 'hours_sale', 'stock_hour6_22_cnt', 'hours_stock_status', 'discount', 'holiday_flag', 'activity_flag', 'precpt', 'avg_temperature', 'avg_humidity', 'avg_wind_level'],\n        num_rows: 350000\n    })\n})\n```\n\n\n## License/Terms of Use\n\nThis dataset is licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0) available at https://creativecommons.org/licenses/by/4.0/legalcode.\n\n**Data Developer:** Dingdong-Inc\n\n\n### Use Case: <br>\nDevelopers researching latent demand recovery and demand forecasting techniques. <br>\n\n### Release Date:  <br>\n05/08/2025 <br>\n\n\n## Data Version\n1.0 (05/08/2025)\n\n\n## Intended use\n\nThe FreshRetailN","encoding":"utf8","key":"README.md","name":"README.md","size":4875,"truncated":true}],"sourceObjectKey":"data/eval.parquet","starterCell":"from datasets import load_dataset\nds = load_dataset(\"Dingdong-Inc/FreshRetailNet-50K\")\nprint(ds)","starterSamplePath":"data/eval.parquet","totalObjects":5},"summary":"FreshRetailNet-50K, described by its authors as the first large-scale benchmark for censored demand estimation in fresh retail.","title":"FreshRetailNet-50K: Fresh Retail Demand with Stockout Annotations","updatedAt":"2026-11-14T17:51:59.129Z","visibility":"public","websiteUrl":"https://github.com/Dingdong-Inc/frn-50k-baseline"}}