Szu-Yao Chien

Posts tagged文章分類

Modelling模型建構

Technical depth, methods, and the craft of building models.技術深度、方法，以及建構模型的實務工藝。

Demand Forecasting with Supervised Learning: Does More Context Help?
Modelling模型建構8 Jun 20262026年6月8日

Demand Forecasting with Supervised Learning: Does More Context Help?監督式需求預測：更多商業情境資訊真的有幫助嗎？

A practical comparison of linear regression and XGBoost across 120 store–SKU series, testing whether promotions, pricing, marketing, competitors, and weather improve one-day-ahead forecasts.以 120 條門市－SKU 序列比較線性迴歸與 XGBoost，檢驗促銷、定價、行銷、競品與天氣資訊能否改善隔日需求預測。

18 min read閱讀約 26 分鐘

Demand Forecasting with Deep Learning: Does an LSTM Earn Its Complexity?
Modelling模型建構5 Jun 20262026年6月5日

Demand Forecasting with Deep Learning: Does an LSTM Earn Its Complexity?深度學習需求預測：LSTM 值得增加的複雜度嗎？

A practical comparison of a global LSTM with XGBoost across 120 store–SKU series, asking whether learned temporal representations justify the added complexity.以 120 條門市－SKU 序列比較全域 LSTM 與 XGBoost，評估學習式時間表徵能否帶來足以抵銷額外成本的預測改善。

18 min read閱讀約 28 分鐘

Demand Forecasting with Statistical Models: How Far Can Demand History Alone Take Us?
Modelling模型建構31 May 20262026年5月31日

Demand Forecasting with Statistical Models: How Far Can Demand History Alone Take Us?僅憑歷史需求，能把需求預測做到多準？

A practical and theoretical guide to forecasting iPhone demand with Holt–Winters and SARIMA—from backtesting and model selection to point forecasts.以 iPhone 隔日需求為例，實作 Holt–Winters 與 SARIMA，完整說明時間序列回測、模型選擇、殘差診斷與預測區間。

20 min read閱讀約 34 分鐘

Forecasting iPhone 17 Pro Demand: From Statistics to Deep Learning
Modelling模型建構28 May 20262026年5月28日

Forecasting iPhone 17 Pro Demand: From Statistics to Deep LearningiPhone 需求預測：從統計模型到深度學習

An Apple Store demand forecasting problem, solved three ways—Statistics, Machine Learning, and LSTM—to explore which model truly earns its complexity.以 Apple Store 的需求規劃為例，比較統計模型、監督式機器學習與 LSTM，說明不同方法在資料規模與商業情境下的適用條件。

14 min read閱讀約 18 分鐘