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?用監督式學習做需求預測：更多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.一項針對 120 條門市－SKU 序列的線性迴歸與 XGBoost 實務比較，測試促銷、定價、行銷、競爭對手與天氣資訊，是否能改善隔日預測。

18 min read閱讀約 27 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?用深度學習做需求預測：LSTM 值得它的複雜度嗎？

A practical comparison of a global LSTM with XGBoost across 120 store–SKU series, asking whether learned temporal representations justify the added complexity.一項針對 120 條門市－SKU 序列的全域 LSTM 與 XGBoost 實務比較，探討學習到的時間表徵，是否值得額外的複雜度。

18 min read閱讀約 29 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，我們能預測到多準？

A practical and theoretical guide to forecasting iPhone demand with Holt–Winters and SARIMA—from backtesting and model selection to point forecasts.一份結合理論與實作的 iPhone 需求預測指南，使用 Holt–Winters 與 SARIMA——涵蓋回測、模型選擇到點預測。

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 Learning預測 iPhone 17 Pro 需求：從統計方法到深度學習

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 的需求預測問題為例，分別用統計方法、機器學習與 LSTM 三種方式來做預測，比較並探討模型在不同商業情境下的適用性。

14 min read閱讀約 19 分鐘