Welcome to Royfactory

Introduction TL;DR: Zhipu, a key player in China’s AI landscape, has experienced a remarkable 120% growth, underscoring the country’s push toward global AI leadership. This development highlights the rapid evolution of China’s AI market and its increasing influence on the global tech ecosystem. China’s burgeoning AI sector is drawing global attention as companies like Zhipu demonstrate exponential growth. With a staggering 120% surge, Zhipu has become a symbol of China’s ambition to dominate the AI industry. This article explores the implications of Zhipu’s recent growth and what it signals for the global AI landscape. ...

Introduction TL;DR: Price elasticity measures how demand responds to price changes, but naive models fail due to endogeneity. Causal and ML-based designs estimate more accurate effects, and scenario simulations help evaluate pricing decisions across demand, revenue, and inventory. (본문은 위 한국어 구조에 대응해 영문으로 동일하게 구성) References (Dynamic modeling and forecasting of price elasticity based on time series analysis and machine learning, 2025)[https://eurekamag.com/research/100/036/100036654.php] (Introduction to price elasticity of demand, 2026-02-14)[https://lilys.ai/notes/1075036] (Price elasticity definitions, accessed 2026-02-14)[https://contents.kocw.or.kr/KOCW/document/2015/korea_sejong/kimmyeongki/04.pdf] (Dynamic Pricing - Causal AI Solutions, accessed 2026-02-14)[https://economicai.com/en-PH/solutions/dynamic-pricing] (Adventures in Demand Analysis Using AI, accessed 2026-02-14)[https://arxiv.org/abs/2501.00382] (Machine learning and operation research based method for promotion optimization, accessed 2026-02-14)[https://www.sciencedirect.com/science/article/abs/pii/S1567422319300912]

Introduction TL;DR: Claude Cowork is a desktop agent mode that can access a user-approved local folder and tools, execute multi-step tasks, and produce real files (docs/spreadsheets/slides). As of 2026-02-11, it’s a research preview available on Claude Desktop (macOS + Windows x64) for paid plans (Pro/Max/Team/Enterprise); Windows arm64 isn’t supported. Why it matters: Agentic power means operational risk. Treat Cowork as a governed tool, not a chat upgrade. What Claude Cowork is (and isn’t) One-sentence definition Claude Cowork is an agentic desktop mode that turns prompts into planned, executed tasks with direct file outputs in a user-approved workspace. ...

Introduction Intermittent Demand Forecasting is a dedicated production track for SKUs with frequent zeros. You should start with Croston-family baselines (Croston/SBA/TSB), then expand to zero-inflated count time-series models only when the data-generating mechanism demands it. TL;DR: Define what “zero” means (true no-demand vs stockout/censoring vs missing), split the pipeline into an intermittent track, and validate with inventory KPIs (service level/cost), not just forecast scores. Why it matters: In intermittent SKUs, average accuracy can look fine while stockouts/overstock explode in a small subset of items. ...

Introduction AI Sales Forecasting often starts with feature-based ML (GBDT). This lesson shows when to move to deep learning and how to use foundation models as fast baselines. TL;DR: pick models based on covariate availability, rolling backtests, calibrated uncertainty, and cost/latency. Why it matters: Deep learning only pays off when it reduces decision risk (stockouts/overstock) at an acceptable operational cost. 1) Model landscape (train-from-scratch vs pretrained) Train-from-scratch: DeepAR, TFT, N-HiTS, TiDE, PatchTST Pretrained foundation models: TimesFM, Chronos, TimeGPT Why it matters: Pretrained models accelerate baselining; train-from-scratch can fit your domain more tightly. ...

Introduction AI Sales Forecasting succeeds in production only if you design the operating loop: monitoring → diagnosis → retrain/rollback. Most failures come from broken inputs and silent distribution shifts, not from model math. TL;DR: Monitor (1) data quality, (2) drift/skew, and (3) post-label performance; then release via a registry with canary and rollback. Why it matters: Forecast labels are often delayed. Drift + data-quality monitoring becomes your early warning system. ...

Introduction TL;DR: AI Sales Forecasting must stay consistent across planning levels (total/category/SKU). The common production pattern is (1) generate base forecasts, then (2) apply forecast reconciliation (e.g., MinT) to enforce coherence. For new items, “cold-start” is solved by borrowing signal from hierarchies and similar items (metadata/content/price tiers). Promotions should be designed either as model features or as a separate uplift (counterfactual) estimation pipeline (e.g., CausalImpact/BSTS). Why it matters: Without coherence, different teams will operate on different numbers, breaking replenishment and planning alignment. ...

Introduction TL;DR: AI Sales Forecasting becomes valuable only when it drives ordering decisions. Build a lead-time (or protection-period) demand distribution, pick the right service metric (CSL vs fill rate), and set reorder point/order-up-to levels using quantiles. Avoid “adding daily P95s” to get a lead-time P95—use sample-path aggregation. For reliable uncertainty, calibrate prediction intervals (e.g., conformal forecasting). Why it matters: Forecast accuracy is not the objective; meeting service targets at minimal total cost is. ...

Introduction TL;DR: AI Sales Forecasting with feature-based ML turns time series into a supervised regression problem using lags/rolling stats, calendar signals, and exogenous variables. The winning recipe is: feature taxonomy → point-in-time correctness → rolling-origin backtests → WAPE → quantile forecasts. Why it matters: This approach scales across many SKUs/stores and stays maintainable when your catalog grows. 1) What “feature-based ML” means for sales forecasting Definition, scope, common misconception Definition: convert time series into a feature table (lags/rollings/calendar/exogenous) and fit a regressor (GBDT). Misconception: “GBDT can’t do time series.” It can, if the feature pipeline and validation are correct. Why it matters: Most failures come from leakage and bad validation, not from the model class. ...

Introduction TL;DR: AI Sales Forecasting must be evaluated using genuine forecasts on unseen data, not training residuals. Use rolling forecasting origin (rolling-origin CV) with explicit choices: horizon, step, window type, and refit policy. Report WAPE + MASE (and pinball loss for quantiles) and compare everything against two fixed baselines: seasonal naive + ETS. In this lecture-style part, you’ll build a backtest setup that matches deployment conditions and produces a decision-ready report. ...