DG·DG · Research Lab

Research for the seller floor.

Technical reports, market research, and methodology notes from the DataGlass Research Lab. Each report is grounded in primary sources, opens its own data, and ends with the operating implication for marketplace sellers.

Lab · 2026
2026
Reports
08
Latest
Sep 1
Cadence
On publish

Available reports.

In reverse-chronological order. Each report links to the full publication; cross-listed market research lives on the blog system but is research-grade.

  1. 02Benchmark report · 2026

    Shopee Ad Benchmarks 2026: What a Click and a Thousand Impressions Actually Cost

    Measured across 333.9M Shopee impressions and 9.11M clicks on 80+ Thai shops: CPC ranges THB 3.36–6.75 and CPM THB 89.16–200.15 by hour of day, while every behavioural input — click-through, conversion, basket, margin — stays inside 1.13–1.42x. The intraday story is an auction price, not a consumer.

    DataGlass Labs ResearchCross-listed from the blog
    September 1, 2026
    Published
    13 min
    Read time
    Intermediate
    Difficulty
  2. 03OPEN DATASET

    Thai marketplace benchmarks

    Aggregated first-party measurements across Thai Shopee shops: what an ad click costs by hour of day, when buyers actually order by category, and the attribution mechanics that make those numbers read wrongly. Observational, aggregate-only, minimum 8 shops per cell. CC BY 4.0.

    DataGlass Research
    August 25, 2026
    Published
    Read time
    Reference
    Difficulty
  3. 04OPEN DATASET

    Marketplace fee schedules, Thailand

    Shopee, Lazada and TikTok Shop Thailand commission and fee schedules — every rate dated and traced to the platform document that published it. CC BY 4.0, with a machine-readable JSON endpoint.

    DataGlass Research
    August 25, 2026
    Published
    Read time
    Reference
    Difficulty
  4. 05Working paper · May 2026

    Mechanism-Aware Hierarchical Causal Elasticity Modeling for Platform E-Commerce

    A methodological working paper proposing MA-HCEM: a hierarchical Bayesian, double-machine-learning, mechanism-aware estimator for SKU-level price elasticity on Shopee, Lazada, and TikTok Shop, with Bundle Deal and voucher mechanisms treated as structured price discrimination.

    Bhum Soonjun · DataGlass Labs Research
    May 7, 2026
    Published
    46 min
    Read time
    Advanced
    Difficulty
  5. 06Research report · May 2026

    Decision Intelligence for E-commerce: How Retailers Optimise Pricing, Forecasting, Inventory, Promotions & Personalization

    Pricing, forecasting, inventory, promotions, and personalization — a deep technical survey of the techniques large retailers use, the variants that matter, and how to deploy them.

    DataGlass Research Lab
    May 4, 2026
    Published
    42 min
    Read time
    Advanced
    Difficulty
  6. 07Working paper · May 2026

    From Gut Feel to Posterior Inference: A Research Article on the DataGlass Decision-Intelligence System for E-Commerce Ad Budget Allocation

    A rigorous public communication of the DataGlass system for daily ad-budget allocation on platform-controlled marketplaces — the analytical reasons rolling-mean heuristics fail, the Bayesian + bandits-with-knapsacks methodology, and the empirical 18–24% portfolio-profit lift.

    DataGlass Research
    May 4, 2026
    Published
    28 min
    Read time
    Advanced
    Difficulty
  7. 08Working paper · May 2026

    Prediction and Risk Optimization Under Uncertainty: A Cross-Domain Meta-Review of Methods in Finance, Operations, Causal Inference, and E-Commerce Decision Intelligence

    A structured meta-review (213 primary works, 254 references) arguing that mature decision systems across finance, operations, insurance, energy, healthcare, causal inference, and e-commerce share four primitives — calibrated probabilistic models, coherent risk-aware objectives, explicit operational constraint sets, and principled exploration. Eleven worked cases ground the framework, with the DataGlass marketplace ad-budget system as the connecting tissue.

    DataGlass Labs Research
    May 4, 2026
    Published
    75 min
    Read time
    Advanced
    Difficulty

Stop guessing. Start deploying.

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