Case studies on public data
We ran 4castPlannr end to end on 13 public datasets, the same way a customer would use it: a plain-English request and a data file. Each case study shows the forecast, the accuracy we measured, the plan where there is one, and every result, including where a simple rule or an existing forecast did better.
Forecasts and plans
-
Yogurt production plan
Public dairy data run end to end: daily sales forecasts for 6 yogurt products and a production plan for one shared line, checked against the next four weeks.
Greece · 19.3% error · 28% better than repeating last season
-
Fresh food reorder plan
Public fresh-retail data: 7-day demand forecasts for the 100 busiest store-product pairs and a reorder plan in whole cases, replayed on the following week.
China · 13% error · 13% better than repeating last season
-
Pizza shop ingredient orders
A synthetic pizza shop: a 14-day sales forecast and a two-week order plan for dough, cheese, sauce and boxes. The rule of thumb won the reality check.
United States (synthetic) · 11.9% error · 23% better than repeating last season · synthetic data
-
Contact center staffing plan
San Francisco 311 public data: daily phone, web and app requests forecast six weeks ahead, and an agent shift plan replayed on the weeks that followed.
San Francisco, United States · 9.8% error · 27% better than repeating last season
-
Grid demand and battery schedule
U.S. EIA grid data: a 7-day hourly demand forecast for 5 balancing authorities, compared with the operators' own forecast, plus a battery schedule for Texas.
United States · 5.7% error · 21% better than repeating last season
-
Online store revenue
A public UK online retailer's order lines turned into a 30-day daily revenue forecast for the Christmas peak, checked against what actually happened.
United Kingdom · 31.4% error · 20% better than repeating last season
-
Wholesale orders for 500 store-product pairs
Iowa's public liquor sales: 8-week forecasts for the 500 biggest store-product pairs. Many items sell in bursts, so the result was flagged for review.
Iowa, United States · 64.6% error · 25% better than repeating last season
-
Hotel room-nights
A public dataset from two hotels: daily room-nights forecast 60 days ahead per hotel, with the accuracy we measured in testing.
Portugal · 29.6% error · 37% better than repeating last season
-
Airport passengers by airline
San Francisco International Airport's public statistics: monthly passengers for the 10 largest airlines forecast a year ahead.
San Francisco, United States · 11.8% error · 38% better than repeating last season
-
Bike rentals with weather
Capital Bikeshare data from the UCI repository: hourly rentals forecast a week ahead, with and without weather as an extra input.
Washington, DC, United States · 28.6% error · 54% better than repeating last season
Messy file tests
The same datasets, deliberately broken the way real exports break: mixed date formats, duplicates, refunds, gaps. The engine had to clean them without help.
-
Messy POS export
The pizza dataset deliberately broken the way real exports break: four date formats, semicolons, missing days, double scans and refunds. Same engine, no hand cleaning.
United States (synthetic) · 15% error · 23% better than repeating last season · synthetic data · messy file test
-
Messy monthly airline file
The SFO passenger data deliberately broken: months written three ways, missing and duplicated rows, negative corrections. Same engine, no hand cleaning.
San Francisco, United States · 12.1% error · 36% better than repeating last season · messy file test
-
Messy daily rentals file
The bike sharing data deliberately broken: tabs, two date styles, missing days, duplicates, 'N/A' temperatures and thousands separators. Same engine, no hand cleaning.
Washington, DC, United States · 27.4% error · 14% better than repeating last season · messy file test