Salesfev / AutoGluon ↗Rossmann Store Daily & Weekly Sales
Benchmark encompassing 1,115 German drugstore locations across daily intervals with a 48-day forecast horizon. Designed for retail demand planning, promo lift evaluation, and store-level revenue prediction.
Business Objective: Rossmann Store Daily & Weekly Sales
01Business Context
Regional store managers and centralized replenishment planners execute daily replenishment cycles and rolling 6-to-7 week inventory commitments across 1,115 chemist/drugstore locations subject to fluctuating consumer footfall, Sunday closures, state-specific school holidays, and marketing promo schedules.
02Analytical Objective
Generate accurate daily sales revenue forecasts per store across a 48-day forward horizon using known calendar promotions and store-specific metadata.
03Economic & Decision Impact
Mitigates over-stocking perishable and fast-moving consumer goods (reducing working capital lockup and holding costs) while preventing costly out-of-stock events and lost gross margin during high-traffic promotional campaigns.
Classical univariate baselines (Seasonal Naive, AutoARIMA) struggle to incorporate multi-store static metadata and intermittent promo interventions. Gradient boosted trees (LightGBM lag pipelines) historically dominated this competition by engineering target-encoded store clusters and promotional lag features, while modern zero-shot foundation models (such as Mistral's Timestral and MOIRAI) demonstrate competitive zero-shot cross-series generalization directly in-context without manual feature engineering.
Target & Feature Column Definitions
Exhaustive business definitions, measurement units, roles, and target variables across all 19 columns.
| Col | Variable / Feature Name | Role | Type | Unit / Scale | Description & Business Meaning |
|---|---|---|---|---|---|
| C | SalesDaily Sales | TARGET | NUM | EUR | Total turnover generated by the store on the specified day. |
| A | idSeries ID | SERIES ID | CAT | — | Unique record or series identifier indexing individual store-level time series trajectories. |
| B | timestampDate | TIME | TIME | — | Daily calendar date corresponding to recorded sales and operational telemetry. |
| D | DayOfWeekDay of Week | Feature | NUM | day | Calendar day of the week represented as an integer (1 = Monday, 7 = Sunday). |
| E | OpenStore Open Status | Feature | NUM | binary flag | Binary indicator specifying whether the store was open (1) or closed (0) for trade. |
| F | PromoPromotional Campaign Active | Feature | NUM | binary flag | Indicator of whether a localized promotional discount campaign is active on that date. |
| G | SchoolHolidaySchool Holiday | Feature | NUM | binary flag | Indicator specifying whether public schools were closed on this date according to regional calendar. |
| H | StateHolidayState Holiday Category | Feature | CAT | — | Categorical flag indicating state holidays (a = public holiday, b = Easter holiday, c = Christmas, 0 = None). |
| I | CustomersCustomer Footfall | Feature | NUM | count | Total customer headcount visiting the store on the day, observed historically. |
| J | AssortmentAssortment Level | Feature | CAT | — | Store assortment depth classification (a = basic, b = extra, c = extended). |
| K | CompetitionDistanceCompetitor Distance | Feature | NUM | meters | Straight-line physical distance in meters to the nearest competing retail store. |
| L | CompetitionOpenSinceMonthCompetitor Open Month | Feature | NUM | month | Approximate month when the nearest competitor opened for business. |
| M | CompetitionOpenSinceYearCompetitor Open Year | Feature | NUM | year | Year when the nearest competitor opened for business. |
| N | Promo2Promo2 Enrolled | Feature | NUM | binary flag | Continuing and consecutive retail promotion participation flag (0 = not participating, 1 = participating). |
| O | Promo2SinceWeekPromo2 Start Week | Feature | NUM | calendar week | Calendar week number when the store started participating in Promo2. |
| P | Promo2SinceYearPromo2 Start Year | Feature | NUM | year | Calendar year when the store began participating in Promo2. |
| Q | PromoIntervalPromo2 Renewal Interval | Feature | CAT | — | Comma-separated consecutive schedule describing which months Promo2 restarts (e.g. 'Feb,May,Aug,Nov'). |
| R | StoreStore Number | Feature | NUM | — | Unique numeric identifier assigned to each individual Rossmann outlet. |
| S | StoreTypeStore Model Type | Feature | CAT | — | Categorical store layout and footprint archetype (a, b, c, d). |
Interactive Data Table
Explore rows, feature values, and target labels for Rossmann Store Daily & Weekly Sales.
Foundation Models vs Traditional ML & Baselines (41 Methods)
Empirical evaluation directly from the AutoGluon fev benchmark suite evaluating zero-shot foundation models against deep learning, gradient-boosted trees, and statistical baselines across 100 evaluation tasks.
| Rank | Method / Model | Family | Organization | SQL Win Rate?Average win rate (%) against all competing models across the benchmark tasks under Scaled Quantile Loss. | SQL Skill?Normalized skill score relative to the Seasonal Naive baseline (0% = baseline, higher is better). | MASE Win Rate?Average win rate (%) under Mean Absolute Scaled Error. | Latency?Median end-to-end execution time per 100 time series in seconds. | Link |
|---|---|---|---|---|---|---|---|---|
| #1 | Timestral-209M | Foundation Model | Mistral AI | 87.7% | +50.4% | 86.0% | 0.51s | Repo ↗ |
| #2 | Timestral-123M (Carla Engine) | Foundation Model | Mistral AI | 86.8% | +50.2% | 85.0% | 0.32s | Repo ↗ |
| #3 | TimeRSI | Closed-Source API | GaTech & SamayLabs | 84.8% | +51.2% | 83.8% | 2512s | Repo ↗ |
| #4 | t0-gamma | Foundation Model | The Forecasting Company | 84.4% | +49.4% | 81.8% | 4.38s | Repo ↗ |
| #5 | Timestral-28M | Foundation Model | Mistral AI | 79.2% | +48.4% | 77.0% | 0.11s | Repo ↗ |
| #6 | timesfm-3 | Foundation Model | 78.5% | +49.0% | 77.0% | 3.41s | Repo ↗ | |
| #7 | ChakraTS | Baseline | Community | 78.2% | +48.1% | 79.5% | 14.22s | Repo ↗ |
| #8 | Lingjiang2.0 | Baseline | Community | 73.9% | +47.0% | 71.3% | 8.89s | Repo ↗ |
| #9 | Chronos-2 | Foundation Model | AWS | 70.4% | +47.3% | 68.4% | 0.84s | Repo ↗ |
| #10 | timeh2o-v1-tiny | Foundation Model | H2O.ai | 69.9% | +45.5% | 67.0% | 0.19s | Repo ↗ |
| #11 | Timestral-5M | Foundation Model | Mistral AI | 69.0% | +46.2% | 67.7% | 40ms | Repo ↗ |
| #12 | Toto-2.0-2.5B | Baseline | Community | 67.5% | +44.4% | 65.7% | 5.58s | Repo ↗ |
| #13 | t0-beta | Foundation Model | The Forecasting Company | 67.4% | +46.6% | 64.5% | 2.29s | Repo ↗ |
| #14 | Toto-2.0-1B | Baseline | Community | 66.4% | +44.4% | 65.5% | 2.48s | Repo ↗ |
| #15 | TiRex-2 | Foundation Model | NX-AI | 65.8% | +45.5% | 63.4% | 0.27s | Repo ↗ |
| #16 | Toto-2.0-313m | Baseline | Community | 65.1% | +44.2% | 63.5% | 1.06s | Repo ↗ |
| #17 | TiRex | Foundation Model | NX-AI | 58.0% | +42.6% | 54.1% | 0.24s | Repo ↗ |
| #18 | Toto-2.0-22m | Baseline | Community | 57.6% | +42.9% | 56.0% | 0.25s | Repo ↗ |
| #19 | TimesFM-2.5 | Baseline | Community | 54.6% | +42.2% | 53.5% | 1.87s | Repo ↗ |
| #20 | TabPFN-TS-3 | Foundation Model | Prior Labs | 52.4% | +43.1% | 51.3% | 235s | Repo ↗ |
| #21 | TS-ICL | Foundation Model | EDF-Lab | 51.2% | +43.1% | 49.8% | 2.49s | Repo ↗ |
| #22 | FlowState | Foundation Model | IBM | 49.3% | +39.9% | 49.9% | 2.29s | Repo ↗ |
| #23 | citras-fm | Foundation Model | Hitachi | 48.8% | +41.2% | 46.9% | 0.60s | Repo ↗ |
| #24 | Toto-1.0 | Baseline | Community | 47.5% | +40.8% | 45.9% | 22.35s | Repo ↗ |
| #25 | TabPFN-TS | Foundation Model | Prior Labs | 47.3% | +41.5% | 45.4% | 109s | Repo ↗ |
| #26 | Toto-2.0-4m | Baseline | Community | 46.2% | +40.7% | 43.6% | 0.20s | Repo ↗ |
| #27 | Moirai-2.0 | Baseline | Community | 41.9% | +39.3% | 40.5% | 0.35s | Repo ↗ |
| #28 | Chronos-Bolt | Foundation Model | AWS | 41.4% | +38.9% | 39.3% | 0.26s | Repo ↗ |
| #29 | TFT | Deep Learning | — | 31.7% | +32.2% | 29.2% | 829s | Repo ↗ |
| #30 | Stat. Ensemble | Baseline | Community | 27.5% | +20.7% | 30.6% | 147s | Repo ↗ |
| #31 | Sundial-Base | Foundation Model | Tsinghua University | 27.4% | +33.4% | 33.6% | 8.01s | Repo ↗ |
| #32 | PatchTST | Deep Learning | — | 26.8% | +30.1% | 25.1% | 664s | Repo ↗ |
| #33 | DeepAR | Deep Learning | — | 26.1% | +29.1% | 23.6% | 1113s | Repo ↗ |
| #34 | AutoARIMA | Statistical Baseline | — | 23.3% | +21.3% | 21.5% | 20.14s | Repo ↗ |
| #35 | AutoETS | Statistical Baseline | — | 20.3% | -26.8% | 22.5% | 3.48s | Repo ↗ |
| #36 | CatBoost | Tree Ensemble | — | 19.1% | +23.0% | 35.1% | 29.48s | Repo ↗ |
| #37 | LightGBM | Tree Ensemble | — | 17.8% | +21.0% | 33.1% | 3.03s | Repo ↗ |
| #38 | AutoTheta | Statistical Baseline | — | 15.6% | +5.5% | 19.8% | 3.28s | Repo ↗ |
| #39 | Seasonal Naive | Baseline | Community | 10.3% | 0.0% | 11.8% | 0.48s | Repo ↗ |
| #40 | Naive | Statistical Baseline | — | 6.7% | -45.4% | 10.9% | 0.47s | Repo ↗ |
| #41 | Drift | Statistical Baseline | — | 6.1% | -45.8% | 10.0% | 0.45s | Repo ↗ |
Variable Schema & Summary Distributions
Observed numerical ranges, category cardinalities, missing rates, and sample values across 1,050,330 rows.
| Col | Variable Name | Type | Missing | Distinct | Summary Stats / Distribution | Sample Values |
|---|---|---|---|---|---|---|
| C | SalesTARGET | NUM | 33,121 (0.03153%) | 21,734 | [0, 41551] μ=5773.8 σ=3849.9 | 055304327 |
| A | id | CAT | 0 | 1,115 | — | 111 |
| B | timestamp | CAT | 0 | 942 | — | 2013-01-01T00:00:002013-01-02T00:00:002013-01-03T00:00:00 |
| D | DayOfWeek | NUM | 0 | 7 | [1, 7] μ=4.0 σ=2.0 | 234 |
| E | Open | NUM | 0 | 2 | [0, 1] μ=0.8 σ=0.4 | 011 |
| F | Promo | NUM | 0 | 2 | [0, 1] μ=0.4 σ=0.5 | 000 |
| G | SchoolHoliday | NUM | 0 | 2 | [0, 1] μ=0.2 σ=0.4 | 111 |
| H | StateHoliday | CAT | 0 | 4 | — | a00 |
| I | Customers | NUM | 33,121 (0.03153%) | 4,086 | [0, 7388] μ=633.1 σ=464.4 | 0668578 |
| J | Assortment | CAT | 0 | 3 | — | aaa |
| K | CompetitionDistance | NUM | 2,826 (0.00269%) | 654 | [20, 75860] μ=5404.9 σ=7659.7 | 127012701270 |
| L | CompetitionOpenSinceMonth | NUM | 333,468 (0.31749%) | 12 | [1, 12] μ=7.2 σ=3.2 | 999 |
| M | CompetitionOpenSinceYear | NUM | 333,468 (0.31749%) | 23 | [1900, 2015] μ=2008.7 σ=6.2 | 200820082008 |
| N | Promo2 | NUM | 0 | 2 | [0, 1] μ=0.5 σ=0.5 | 000 |
| O | Promo2SinceWeek | NUM | 512,448 (0.48789%) | 24 | [1, 50] μ=23.6 σ=14.1 | 404040 |
| P | Promo2SinceYear | NUM | 512,448 (0.48789%) | 7 | [2009, 2015] μ=2011.8 σ=1.7 | 201420142014 |
| Q | PromoInterval | CAT | 512,448 (0.48789%) | 3 | — | Jan,Apr,Jul,OctJan,Apr,Jul,OctJan,Apr,Jul,Oct |
| R | Store | NUM | 0 | 1,115 | [1, 1115] μ=558.0 σ=321.9 | 111 |
| S | StoreType | CAT | 0 | 4 | — | ccc |
Frequently Asked Questions: Rossmann Store Daily & Weekly Sales
Common questions regarding the Rossmann Store Daily & Weekly Sales dataset, machine learning task formulations, and in-browser tabular inference.
What is the forecasting horizon for Rossmann Store Daily & Weekly Sales?
The benchmark horizon is 48 daily steps (~7 weeks), matching commercial replenishment and tactical operational planning cycles for retail store chains.
Can I run zero-server forecasts on this dataset in Google Sheets?
Yes, Carla enables zero-server in-context time series forecasting directly in spreadsheets using Mistral's Timestral foundation model.
Which models perform best on Rossmann Store Daily & Weekly Sales?
Historically, gradient boosted decision trees (LightGBM) with lagged sales features scored highest in competition settings, while modern foundation models (such as Mistral's Timestral and MOIRAI) deliver top-tier zero-shot cross-store generalization without hand-crafted feature engineering.
Test TabICLv2 on Rossmann Store Daily & Weekly Sales Yourself
Open the pre-loaded Google Sheet and let Carla configure the target and task for local, zero-cloud tabular machine learning.
Launch Carla
Click once to open the spreadsheet and Carla side panel together.
Review the Setup
Carla selects the dataset target and task from this page automatically.
Evaluate & Predict
Run predictions and compute metrics with zero server uploads.
Provenance & Attribution
Rossmann Store Sales Prediction Benchmark, Kaggle Inc. & Dirk Rossmann GmbH, 2015.