Demand Forecasting Best Practices by Nicolas Vandeput
Author:Nicolas Vandeput [Vandeput, Nicolas]
Language: eng
Format: epub, pdf
Publisher: Manning Publications Co.
Published: 2023-05-15T22:00:00+00:00
Hammer
100
150
20â¬
2,000â¬
3,000â¬
50
50
2,500
1,000â¬
1,000â¬
1,000,000â¬
Nail
1,500
1,000
0.1â¬
150â¬
100â¬
â 500
500
250,000
â50â¬
50â¬
2,500â¬
Total
1,612
1,160
2,750â¬
3,600â¬
â 452
552
290
850â¬
1,150â¬
581â¬
â 28%
34%
18%
31%
42%
21%
Note that you can weight products based on their costs, margins, or sale prices. Or even based on arbitrary weights to reflect their strategic importance.
As you can see in tables 11.3 and 11.4, RMSE scales poorly to product portfolios. And its value-weighted counterpart doesnât scale well either. As RMSE is squaring errors, it will always put too much emphasis on high-volume items. RMSE might be a good KPI to assess the accuracy of a single product, but it shouldnât be used over portfolios.
Pro Tip: Penalties for over- and under-forecasting?
There is a temptation to penalize (or weight) positive and negative forecast errors differently with a tool such as weighted errors. Obviously, in supply chains, the cost of having one product too many (extra holding costs or spoilage) or one product too few (unhappy clients, lost revenues) is not the same. Nevertheless, you will get biased forecasts by giving more importance to over or under forecasts. This will, in turn, gradually reduce the confidence in the overall forecasting process, until other teams and planners start creating their own projections because they do not trust the main demand forecast anymore. It is always better to balance company priorities regarding risks, costs, and service levels by setting proper service level targets and allocating the right amount of safety stock for each product. For more information, see my book Inventory Optimizations: Models and Simulations.
Download
Demand Forecasting Best Practices by Nicolas Vandeput.pdf
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.
Access | Data Mining |
Data Modeling & Design | Data Processing |
Data Warehousing | MySQL |
Oracle | Other Databases |
Relational Databases | SQL |
Algorithms of the Intelligent Web by Haralambos Marmanis;Dmitry Babenko(7895)
Learning SQL by Alan Beaulieu(5465)
Weapons of Math Destruction by Cathy O'Neil(5094)
Big Data Analysis with Python by Ivan Marin(3269)
Building Statistical Models in Python by Huy Hoang Nguyen & Paul N Adams & Stuart J Miller(2969)
Azure Data and AI Architect Handbook by Olivier Mertens & Breght Van Baelen(2955)
Blockchain Basics by Daniel Drescher(2928)
Serverless Machine Learning with Amazon Redshift ML by Debu Panda & Phil Bates & Bhanu Pittampally & Sumeet Joshi(2863)
Data Wrangling on AWS by Navnit Shukla | Sankar M | Sam Palani(2650)
Hands-On Machine Learning for Algorithmic Trading by Stefan Jansen(2603)
Pandas Cookbook by Theodore Petrou(2527)
Mastering Python for Finance by Unknown(2526)
Driving Data Quality with Data Contracts by Andrew Jones(2526)
Data Engineering with dbt by Roberto Zagni(2347)
Machine Learning Model Serving Patterns and Best Practices by Md Johirul Islam(2317)
How The Mind Works by Steven Pinker(2253)
Network Science with Python and NetworkX Quick Start Guide by Edward L. Platt(2084)
Building Machine Learning Systems with Python by Richert Willi Coelho Luis Pedro(2073)
Learn T-SQL Querying by Pam Lahoud & Pedro Lopes(2056)