MFG Forecasting/Data Analysis

Dataset analysis

Explore and analyse all 15 datasets. Click a card to load its statistical profile, or build it from raw files.

Analysing

active dataset

Dataset catalog — 12 cached · 3 buildable · 0 files missing

Filter:

Historical Product Demand

Product × warehouse order demand from a manufacturer. Most representative for production planning.

weekly1.05M rows → weeklyKaggle — felixzhao

✓ cached

Store Item Demand Forecasting

10 stores × 50 items, 5 years daily demand aggregated to weekly. Clean sandbox dataset.

weekly913k rows → weeklyKaggle competition

✓ cached

Food Demand Forecasting (Genpact)

77 fulfillment centers × 51 meals, weekly orders with price and promotion signals.

weekly457k rows (weekly native)Kaggle — Genpact

✓ cached

Rossmann Store Sales

1,115 German pharmacy stores, 2.5 years daily sales aggregated to weekly.

weekly1.02M rows → weeklyKaggle competition

✓ cached

Predict Future Sales (1C Russia)

60 shops × 21k items, daily transactions aggregated to monthly demand.

monthly2.94M rows → monthlyKaggle competition

✓ cached

M5 Forecasting — Walmart (sample)

Top-50 series from 30,490 Walmart item×store series. Hierarchical, price-enriched.

weekly30k × 1941 days → weekly sampleKaggle competition (M5)

✓ cached

Favorita Grocery Sales (sample)

Top-40 store×item series from Ecuador Favorita (125M rows). External regressors available.

weekly125M rows → weekly sampleKaggle competition

✓ cached

Shopify Sales (synthetic)

Synthetic 60k orders. Weekly revenue per product category. Good for EDA demos.

weekly60k orders → weeklyKaggle

✓ cached

Dunnhumby — The Complete Journey

2.5M basket transactions, 2,500 households. Best for promo/coupon uplift modelling.

transaction2.6M basket lines → weeklyKaggle

✓ cached

UCI Online Retail

UK online gift retailer invoices, 2010–2011.

transaction~542k invoice lines → weeklyUCI ML Repository

UCI Online Retail II

Extended 2009–2011 version of UCI Online Retail.

transaction~1M invoice lines → weeklyUCI ML Repository

Retailrocket E-commerce

2.76M clickstream events. Purchase events give a weekly item-demand proxy.

transaction2.76M events → weekly (purchases)Kaggle

✓ cached

Amazon Sales Dataset

1,465 Amazon India products with prices and reviews. No time axis.

static1,465 productsKaggle

not buildable

M4 Competition

100,000 anonymized univariate series across 6 frequencies. Top monthly series shown.

monthly48k monthly series → top-NGitHub — Mcompetitions

✓ cached

Platform Demand (current)

Pre-built platform dataset (Historical Product Demand, top-16 SKUs). Currently active.

weekly16 SKUs × 140 weeksbackend/data/platform_demand.json

✓ cached

Cached (ready)

Raw files present (click Build)

Files not found

1 · Dataset overview

SKUs

series

Periods

274

weekly observations

Category	SKUs	Mean demand / SKU	Portfolio share
FOODS	17	445.7	71.8%
HOBBIES	17	67.3	10.8%
HOUSEHOLD	17	107.5	17.3%

2 · Per-SKU demand statistics

SKU	Category	Mean	Median	Std dev	CV	P10	P90	Zero wks	Trend slope	Autocorr
FOODS_3_090_CA_3	FOODS	914.2	908	648.8	0.71	0	1.7K	31 (11.3%)	-1.04	0.80
FOODS_3_586_TX_2	FOODS	703.8	687	133.7	0.19	547.9	889.1	0	-0.57	0.72
FOODS_3_586_TX_3	FOODS	547.9	537	123.5	0.23	397	705.2	0	-0.83	0.76
FOODS_3_586_CA_3	FOODS	490.5	484	74.3	0.15	404.3	579	0	+0.25	0.51
FOODS_3_090_CA_1	FOODS	464.2	480	324	0.70	0	807.7	55 (20.1%)	-0.20	0.79
FOODS_3_090_WI_3	FOODS	443.2	471.5	309.7	0.70	0	820.2	56 (20.4%)	+0.18	0.78
FOODS_3_090_TX_2	FOODS	436.1	446.5	311.9	0.72	0	741.7	56 (20.4%)	-0.13	0.72
FOODS_3_090_TX_3	FOODS	419.2	463	265.9	0.63	0	712.8	55 (20.1%)	+0.08	0.73
FOODS_3_252_TX_2	FOODS	416.6	404	99.5	0.24	308.6	558.7	0	-0.10	0.73
FOODS_3_586_TX_1	FOODS	410.4	399	96.8	0.24	302.3	535	0	-0.60	0.75
FOODS_3_226_WI_3	FOODS	358.5	354.5	66.6	0.19	278	443.7	0	-0.07	0.59
FOODS_3_555_TX_2	FOODS	355.8	343	84.4	0.24	266	478.7	0	-0.55	0.74
FOODS_3_090_TX_1	FOODS	341.9	359	261.4	0.76	0	626.3	57 (20.8%)	+0.05	0.75
FOODS_3_120_CA_3	FOODS	324.1	384	292.6	0.90	0	655.4	86 (31.4%)	+2.05	0.88
FOODS_3_586_CA_1	FOODS	320	313.5	61.2	0.19	249	399.4	0	-0.13	0.59
FOODS_3_252_TX_3	FOODS	316.2	304	96.2	0.30	203	432	0	-0.33	0.82
FOODS_3_586_WI_3	FOODS	314.2	283.5	105	0.33	199	470.1	0	-1.05	0.86
HOBBIES_1_234_CA_3	HOBBIES	108.5	81.5	102.9	0.95	0	253.9	47 (17.2%)	+0.97	0.71
HOBBIES_1_348_CA_1	HOBBIES	83	82	52.7	0.63	0	153.4	30 (10.9%)	+0.08	0.48
HOBBIES_1_371_CA_1	HOBBIES	82.5	90	43.6	0.53	0.3	129.7	28 (10.2%)	-0.02	0.42
HOBBIES_1_254_CA_3	HOBBIES	76.6	72	32.9	0.43	39	125	1 (0.4%)	+0.03	0.43
HOBBIES_1_371_CA_3	HOBBIES	72.3	71.5	43	0.59	2.6	128	22 (8%)	-0.03	0.55
HOBBIES_1_348_CA_3	HOBBIES	70.8	64	55.1	0.78	2	141.1	24 (8.8%)	-0.28	0.62
HOBBIES_1_268_CA_1	HOBBIES	69	66	43.3	0.63	1.3	120.7	27 (9.9%)	-0.08	0.45
HOBBIES_1_341_CA_3	HOBBIES	65.1	66	40.6	0.62	4.3	114	14 (5.1%)	-0.07	0.58
HOBBIES_1_015_CA_3	HOBBIES	64.3	61	28.6	0.44	29.3	101	1 (0.4%)	-0.08	0.52
HOBBIES_1_268_CA_3	HOBBIES	61.9	50	48	0.77	4.3	129.6	20 (7.3%)	-0.07	0.60
HOBBIES_1_008_CA_3	HOBBIES	60.8	47.5	57.2	0.94	1	150.4	26 (9.5%)	-0.31	0.81
HOBBIES_1_178_CA_1	HOBBIES	57.7	61.5	32.4	0.56	0.3	99	28 (10.2%)	-0.07	0.51
HOBBIES_1_256_CA_1	HOBBIES	56.3	53	37.9	0.67	0	101.7	31 (11.3%)	-0.13	0.58
HOBBIES_1_254_CA_1	HOBBIES	54.9	51.5	24.5	0.45	29.3	85.4	1 (0.4%)	+0.03	0.16
HOBBIES_1_233_CA_3	HOBBIES	54.8	49.5	29.1	0.53	26	89.7	3 (1.1%)	-0.09	0.33
HOBBIES_1_370_CA_1	HOBBIES	53.2	47.5	44.2	0.83	0	108.7	36 (13.1%)	-0.22	0.64
HOBBIES_1_371_CA_4	HOBBIES	52.8	52	28.3	0.54	4	89	27 (9.9%)	-0.04	0.45
HOUSEHOLD_1_118_CA_3	HOUSEHOLD	158.2	151	61.6	0.39	101.3	216.7	0	-0.16	0.41
HOUSEHOLD_1_459_CA_3	HOUSEHOLD	134.9	150	96.2	0.71	0	244.7	70 (25.5%)	+0.56	0.84
HOUSEHOLD_1_334_CA_3	HOUSEHOLD	134.3	139	103.1	0.77	0	277.9	70 (25.5%)	+0.38	0.87
HOUSEHOLD_1_303_CA_3	HOUSEHOLD	127.4	122	70	0.55	39.3	219.1	2 (0.7%)	-0.10	0.69
HOUSEHOLD_1_521_CA_3	HOUSEHOLD	110.5	111	53.9	0.49	47.3	179.8	5 (1.8%)	+0.05	0.63
HOUSEHOLD_1_459_WI_2	HOUSEHOLD	107.6	112.5	82.4	0.77	0	217.2	70 (25.5%)	+0.65	0.69
HOUSEHOLD_1_465_CA_3	HOUSEHOLD	107.6	122.5	75.3	0.70	0	198	70 (25.5%)	+0.60	0.86
HOUSEHOLD_1_351_CA_3	HOUSEHOLD	104.5	99.5	87	0.83	0	229.4	70 (25.5%)	+0.22	0.88
HOUSEHOLD_1_019_CA_3	HOUSEHOLD	103.7	111	76.4	0.74	0	205	70 (25.5%)	+0.49	0.83
HOUSEHOLD_1_110_WI_2	HOUSEHOLD	101.4	108.5	88.1	0.87	0	204.7	85 (31%)	+0.65	0.81
HOUSEHOLD_1_277_CA_3	HOUSEHOLD	101.3	100.5	84.4	0.83	0	214	76 (27.7%)	+0.43	0.84
HOUSEHOLD_1_339_CA_3	HOUSEHOLD	98.6	93.5	84.3	0.86	0	216.8	76 (27.7%)	+0.41	0.80
HOUSEHOLD_1_110_CA_3	HOUSEHOLD	89.7	108.5	83.7	0.93	0	183	108 (39.4%)	+0.73	0.90
HOUSEHOLD_1_334_WI_2	HOUSEHOLD	87.3	89	69.2	0.79	0	177.7	70 (25.5%)	+0.46	0.71
HOUSEHOLD_1_535_CA_3	HOUSEHOLD	87.2	91	44.3	0.51	15.6	142.4	9 (3.3%)	-0.06	0.51
HOUSEHOLD_1_447_CA_3	HOUSEHOLD	87	99	62.2	0.71	0	160.4	70 (25.5%)	+0.38	0.84
HOUSEHOLD_1_083_CA_3	HOUSEHOLD	86	84	37.4	0.44	40.3	132	5 (1.8%)	-0.26	0.75

CV = coefficient of variation (std/mean). Higher = more volatile. Trend slope = units/period from OLS. Autocorr = lag-1 Pearson.

3 · Rankings

Volume rankingmean demand ↓

1	FOODS_3_090_CA_3	FOODS	914.2
2	FOODS_3_586_TX_2	FOODS	703.8
3	FOODS_3_586_TX_3	FOODS	547.9
4	FOODS_3_586_CA_3	FOODS	490.5
5	FOODS_3_090_CA_1	FOODS	464.2
6	FOODS_3_090_WI_3	FOODS	443.2
7	FOODS_3_090_TX_2	FOODS	436.1
8	FOODS_3_090_TX_3	FOODS	419.2
9	FOODS_3_252_TX_2	FOODS	416.6
10	FOODS_3_586_TX_1	FOODS	410.4
11	FOODS_3_226_WI_3	FOODS	358.5
12	FOODS_3_555_TX_2	FOODS	355.8
13	FOODS_3_090_TX_1	FOODS	341.9
14	FOODS_3_120_CA_3	FOODS	324.1
15	FOODS_3_586_CA_1	FOODS	320

Volatility rankingCV ↓

1	HOBBIES_1_234_CA_3	HOBBIES	0.95
2	HOBBIES_1_008_CA_3	HOBBIES	0.94
3	HOUSEHOLD_1_110_CA_3	HOUSEHOLD	0.93
4	FOODS_3_120_CA_3	FOODS	0.90
5	HOUSEHOLD_1_110_WI_2	HOUSEHOLD	0.87
6	HOUSEHOLD_1_339_CA_3	HOUSEHOLD	0.86
7	HOUSEHOLD_1_277_CA_3	HOUSEHOLD	0.83
8	HOUSEHOLD_1_351_CA_3	HOUSEHOLD	0.83
9	HOBBIES_1_370_CA_1	HOBBIES	0.83
10	HOUSEHOLD_1_334_WI_2	HOUSEHOLD	0.79
11	HOBBIES_1_348_CA_3	HOBBIES	0.78
12	HOBBIES_1_268_CA_3	HOBBIES	0.77
13	HOUSEHOLD_1_334_CA_3	HOUSEHOLD	0.77
14	HOUSEHOLD_1_459_WI_2	HOUSEHOLD	0.77
15	FOODS_3_090_TX_1	FOODS	0.76

Aggregate demand timeline — all SKUs combined

Per-SKU recent demand (last 8 weeks)

FOODS_3_090_CA_3

FOODS_3_586_TX_2

FOODS_3_586_TX_3

FOODS_3_586_CA_3

FOODS_3_090_CA_1

FOODS_3_090_WI_3

FOODS_3_090_TX_2

FOODS_3_090_TX_3

FOODS_3_252_TX_2

FOODS_3_586_TX_1

FOODS_3_226_WI_3

FOODS_3_555_TX_2

FOODS_3_090_TX_1

FOODS_3_120_CA_3

FOODS_3_586_CA_1

FOODS_3_252_TX_3

FOODS_3_586_WI_3

HOBBIES_1_234_CA_3

HOBBIES_1_348_CA_1

HOBBIES_1_371_CA_1

HOBBIES_1_254_CA_3

HOBBIES_1_371_CA_3

HOBBIES_1_348_CA_3

HOBBIES_1_268_CA_1

HOBBIES_1_341_CA_3

HOBBIES_1_015_CA_3

HOBBIES_1_268_CA_3

HOBBIES_1_008_CA_3

HOBBIES_1_178_CA_1

HOBBIES_1_256_CA_1

HOBBIES_1_254_CA_1

HOBBIES_1_233_CA_3

HOBBIES_1_370_CA_1

HOBBIES_1_371_CA_4

HOUSEHOLD_1_118_CA_3

HOUSEHOLD_1_459_CA_3

HOUSEHOLD_1_334_CA_3

HOUSEHOLD_1_303_CA_3

HOUSEHOLD_1_521_CA_3

HOUSEHOLD_1_459_WI_2

HOUSEHOLD_1_465_CA_3

HOUSEHOLD_1_351_CA_3

HOUSEHOLD_1_019_CA_3

HOUSEHOLD_1_110_WI_2

HOUSEHOLD_1_277_CA_3

HOUSEHOLD_1_339_CA_3

HOUSEHOLD_1_110_CA_3

HOUSEHOLD_1_334_WI_2

HOUSEHOLD_1_535_CA_3

HOUSEHOLD_1_447_CA_3

HOUSEHOLD_1_083_CA_3

Seasonality index — normalised monthly demand (1.0 = average)

Index > 1.0 = above-average demand month. Dashed line = overall average.

Demand distribution per SKU — P10 / P25 / Median / P75 / P90

Dark bar = interquartile range (P25–P75). Light bars = P10–P25 and P75–P90.

4 · Cross-SKU correlation (top pairs)

SKU A	SKU B	Pearson r	Strength
HOUSEHOLD_1_459_WI_2	HOUSEHOLD_1_334_WI_2	0.940	strong	move together
HOUSEHOLD_1_334_CA_3	HOUSEHOLD_1_351_CA_3	0.927	strong	move together
HOUSEHOLD_1_459_CA_3	HOUSEHOLD_1_447_CA_3	0.915	strong	move together
HOUSEHOLD_1_277_CA_3	HOUSEHOLD_1_339_CA_3	0.909	strong	move together
HOUSEHOLD_1_459_CA_3	HOUSEHOLD_1_334_CA_3	0.903	strong	move together
FOODS_3_090_CA_3	FOODS_3_090_CA_1	0.899	strong	move together
FOODS_3_090_CA_1	FOODS_3_090_TX_2	0.896	strong	move together
HOUSEHOLD_1_334_CA_3	HOUSEHOLD_1_447_CA_3	0.887	strong	move together
FOODS_3_090_TX_2	FOODS_3_090_TX_3	0.886	strong	move together
FOODS_3_090_TX_2	FOODS_3_090_TX_1	0.885	strong	move together
FOODS_3_090_CA_1	FOODS_3_090_TX_3	0.876	strong	move together
FOODS_3_090_CA_3	FOODS_3_090_TX_3	0.876	strong	move together
FOODS_3_090_TX_3	FOODS_3_090_TX_1	0.870	strong	move together
FOODS_3_090_CA_1	FOODS_3_090_TX_1	0.864	strong	move together
FOODS_3_090_WI_3	FOODS_3_090_TX_3	0.850	strong	move together
FOODS_3_090_CA_3	FOODS_3_090_TX_2	0.849	strong	move together
HOUSEHOLD_1_351_CA_3	HOUSEHOLD_1_447_CA_3	0.849	strong	move together
HOUSEHOLD_1_459_CA_3	HOUSEHOLD_1_465_CA_3	0.843	strong	move together
FOODS_3_090_WI_3	FOODS_3_090_TX_2	0.839	strong	move together
HOUSEHOLD_1_459_CA_3	HOUSEHOLD_1_351_CA_3	0.838	strong	move together

Pearson r. Strong ≥0.7 · Moderate ≥0.4 · Weak <0.4.

5 · Raw data sample — last 8 periods

Date	FOODS_3_090_CA_3	FOODS_3_586_TX_2	FOODS_3_586_TX_3	FOODS_3_586_CA_3	FOODS_3_090_CA_1	FOODS_3_090_WI_3	FOODS_3_090_TX_2	FOODS_3_090_TX_3	FOODS_3_252_TX_2	FOODS_3_586_TX_1	FOODS_3_226_WI_3	FOODS_3_555_TX_2
Feb 29, 2016	719	614	458	437	365	611	431	414	424	320	384	304
Mar 7, 2016	818	607	434	454	365	544	426	489	382	323	368	335
Mar 14, 2016	694	634	430	373	356	536	467	483	436	324	371	341
Mar 21, 2016	887	601	476	505	427	595	512	436	381	401	346	359
Mar 28, 2016	727	532	385	406	300	534	432	377	361	327	338	312
Apr 4, 2016	740	594	444	501	371	549	448	430	375	425	303	324
Apr 11, 2016	862	510	415	484	371	582	453	455	312	337	344	281
Apr 18, 2016	761	492	387	483	381	593	395	461	324	421	300	258

Showing first 12 of 51 SKUs.

6 · Zero-demand periods (intermittent SKUs)

SKU	Zero periods	Zero %	Risk
FOODS_3_090_CA_3	31	11.3%	medium intermittency
FOODS_3_090_CA_1	55	20.1%	high intermittency
FOODS_3_090_WI_3	56	20.4%	high intermittency
FOODS_3_090_TX_2	56	20.4%	high intermittency
FOODS_3_090_TX_3	55	20.1%	high intermittency
FOODS_3_090_TX_1	57	20.8%	high intermittency
FOODS_3_120_CA_3	86	31.4%	high intermittency
HOBBIES_1_234_CA_3	47	17.2%	medium intermittency
HOBBIES_1_348_CA_1	30	10.9%	medium intermittency
HOBBIES_1_371_CA_1	28	10.2%	medium intermittency
HOBBIES_1_254_CA_3	1	0.4%	low intermittency
HOBBIES_1_371_CA_3	22	8%	medium intermittency
HOBBIES_1_348_CA_3	24	8.8%	medium intermittency
HOBBIES_1_268_CA_1	27	9.9%	medium intermittency
HOBBIES_1_341_CA_3	14	5.1%	medium intermittency
HOBBIES_1_015_CA_3	1	0.4%	low intermittency
HOBBIES_1_268_CA_3	20	7.3%	medium intermittency
HOBBIES_1_008_CA_3	26	9.5%	medium intermittency
HOBBIES_1_178_CA_1	28	10.2%	medium intermittency
HOBBIES_1_256_CA_1	31	11.3%	medium intermittency
HOBBIES_1_254_CA_1	1	0.4%	low intermittency
HOBBIES_1_233_CA_3	3	1.1%	low intermittency
HOBBIES_1_370_CA_1	36	13.1%	medium intermittency
HOBBIES_1_371_CA_4	27	9.9%	medium intermittency
HOUSEHOLD_1_459_CA_3	70	25.5%	high intermittency
HOUSEHOLD_1_334_CA_3	70	25.5%	high intermittency
HOUSEHOLD_1_303_CA_3	2	0.7%	low intermittency
HOUSEHOLD_1_521_CA_3	5	1.8%	low intermittency
HOUSEHOLD_1_459_WI_2	70	25.5%	high intermittency
HOUSEHOLD_1_465_CA_3	70	25.5%	high intermittency
HOUSEHOLD_1_351_CA_3	70	25.5%	high intermittency
HOUSEHOLD_1_019_CA_3	70	25.5%	high intermittency
HOUSEHOLD_1_110_WI_2	85	31%	high intermittency
HOUSEHOLD_1_277_CA_3	76	27.7%	high intermittency
HOUSEHOLD_1_339_CA_3	76	27.7%	high intermittency
HOUSEHOLD_1_110_CA_3	108	39.4%	high intermittency
HOUSEHOLD_1_334_WI_2	70	25.5%	high intermittency
HOUSEHOLD_1_535_CA_3	9	3.3%	low intermittency
HOUSEHOLD_1_447_CA_3	70	25.5%	high intermittency
HOUSEHOLD_1_083_CA_3	5	1.8%	low intermittency

7 · Calendar events — holidays & promotions in range

This dataset has no calendar-event data. Select M5 — Walmart or Favorita to see real holidays and events.

Events are snapped to their ISO week to align with the weekly demand timeline above. Use them to read demand spikes — e.g. holidays and promotional weeks.