『您的瀏覽器不支援JavaScript功能,若網頁功能無法正常使用時,請開啟瀏覽器JavaScript狀態』

跳到主要內容區塊

工業技術研究院

:::

技術名稱: 供需預測技術

技術簡介

供需預測為業界痛點,當預測不準,易造成庫存量過高導致成本流失、庫存不足導致無法維修或是無商品可販售,本技術透過特徵擷取、相似模型比對,結合時序迴歸模型建立需求預測模型,可廣泛應用於不同業態。

Abstract

Supply and demand forecasting is the pain point in industry. Bad forecasts causes too much inventory or insufficient inventory, both of which affect commercial profits. The demand forecasting techniques contain feature extraction, similar model searching, and time-series regression model construction, able to be used in many distinct applications.

技術規格

供需預測包含時序迴歸模型與相似模型比對方法,透過時序迴歸模型與相似模型比對方法,可預測下一時間點的需求量與未來一段時間點的需求總量。本技術在平穩型需求之預測下一時間點的需求量準確度(MAPE)可低於20%。

Technical Specification

The demand forecasting techniques contain feature extraction, similar model searching, and time-series regression model construction. By the similar model searching method, we can predict the requirement amounts in the next time point and also the total requirement amounts of a time period in the future. MAPE of these models on smooth demands can be less than 20%.

技術特色

本技術涵蓋需求可預測性檢驗,針對具可預測性需求使用XGB、Lasso、SVR等機器學習演算法與DNN、LSTM、CNN等深度學習演算法進行預測模型建模,並透過遷移式學習解決訓練資料數量可能不足的問題,在平穩型需求預測MAPE可穩定維持低於20%。

應用範圍

供需預測需求為業界痛點,可廣泛應用於不同業態;包含品牌商、ODM、製造商、通路或服務供應商等。

接受技術者具備基礎建議(設備)

python、sklearn、keras。

接受技術者具備基礎建議(專業)

具資料分析、機器學習、深度學習與python開發基本知識。

技術分類 智慧商務技術及服務

聯絡資訊

聯絡人:姜林宛樺 執行長室

電話:03-5917919 或 Email:lily@itri.org.tw

客服專線:+886-800-45-8899

傳真:03-5910257

[{"text":"企業網","weight":13.0},{"text":"材化所","weight":11.5},{"text":"機械所","weight":10.0},{"text":"綠能所","weight":9.4},{"text":"生醫所","weight":8.0},{"text":"半導體","weight":6.2},{"text":"南分院","weight":5.0},{"text":"太陽能","weight":5.0},{"text":"課程","weight":5.0},{"text":"遠紅外線","weight":5.0},{"text":"雷射","weight":4.0},{"text":"LED","weight":4.0},{"text":"LED可見光","weight":3.0},{"text":"5G","weight":3.0},{"text":"工研人","weight":3.0},{"text":"電光所","weight":3.0},{"text":"綠能與環境研究所","weight":3.0},{"text":"機械","weight":3.0},{"text":"資通所","weight":2.0},{"text":"面板","weight":2.0},{"text":"文字轉語音","weight":2.0},{"text":"實習","weight":2.0},{"text":"無人機","weight":2.0},{"text":"生醫","weight":2.0},{"text":"3D","weight":2.0},{"text":"v2x","weight":2.0},{"text":"員工","weight":2.0},{"text":"地圖","weight":2.0},{"text":"太陽光電","weight":2.0},{"text":"材料與化工研究所","weight":1.0}]