00/Architecture

The three pillars you see, the three you don't.

Instead of a feature list, DataGlass is organised in two tiers. Top: what sellers see — true profit optimisation, automated decision making, risk management. Below: the engine that makes those claims real — operations research, financial modelling, machine learning. Each pillar cites the blog posts and research that prove it.

↳ Pillars

01 · Pillar

True Profit Optimization

Margin is the goal, not GMV.

DataGlass models true profit per SKU — net of platform commission, transaction fees, seller-funded vouchers, ad attribution, cancellations, returns, VAT, and logistics. Every recommendation respects the SKU's own break-even bar, not a single account-wide ROAS target. Margin reconstruction at order-line granularity, returns-reserve provisioning, and probabilistic price-elasticity per SKU make the cost stack precise enough to act on.

02 · Pillar

Automated Decision Making

From decisions to deployment, not dashboards.

A ranked, profit-maximising action queue. Bid adjustments, voucher tiers, and listing optimisations all ship in one click against the native Shopee, Lazada, and TikTok Shop flow — with post-deployment tracking against expected lift. Operations research drives the queue — budget allocation across heterogeneous campaigns, dynamic pricing under demand uncertainty, inventory policy under stochastic lead time, voucher-tier discipline against category-margin constraints.

03 · Pillar

Risk Management

Every action passes the safety bar before it ships.

Margin floors, budget caps, price-change limits, seller approval gates, and post-deployment measurement against expected profit and downside. Recommendations that fail any guardrail don't deploy — regardless of expected value. Robust optimisation puts a hard floor under every decision — CVaR-95 below the margin floor is not deployed. Bayesian and causal inference are the underlying inference machinery.

↳ Foundations

  1. I. Foundation

    Operations research

    — Without selling more or spending more, where does profit come from?

    Operations research answers the question rigorously: budget allocation across heterogeneous campaigns, dynamic pricing under demand uncertainty, inventory policy under stochastic lead time, voucher-tier discipline against category-margin constraints. The math that says "cut here, reallocate there, wait for that" — proven before it deploys, with Bayesian and causal methods used inline as the underlying inference machinery.

  2. II. Foundation

    Risk-aware optimisation

    — The finance + uncertainty modelling that keeps the optimum honest.

    Robust optimisation puts a hard floor under every decision. Worst-case scenarios are modelled and capped before any action ships — CVaR-95 below the margin floor is not deployed, regardless of how high the expected value sits. Margin reconstruction down to the order line, returns-reserve provisioning, working-capital modelling under campaign-driven demand spikes, and probabilistic price-elasticity estimation per SKU make the cost stack precise enough that the risk math has something real to bound.

Stop guessing. Start deploying.

Join the sellers using DataGlass to turn shop data into the next profit-maximizing action.