Bayesian
Bayesian EXAWin-Rate Forecaster
Precisely predict sales success by real-time Bayesian updates of subtle signals from every negotiation. With EXAWin, sales evolves from intuition into the ultimate data science.
The Line PQC Case: Managing Defects as Evidence, Not Assumptions
A supply chain business scenario based on the primary manufacturing line as the reference process. It explains how an NG detected during roaming line PQC is connected to LOT, line, position, defect type, disposition status, supplied-part risk, and delivery impact. It also shows how paper- and Excel-based quality records are standardized inside Exa Omni+, and how repeated evidence updates risk judgment.
The Moment One POP Entry Continues All the Way to Shipment: A Day of Line Execution Control
A business scenario describing how an operator's POP result entry on an electric blanket production line continues into line-side inventory, WIP status, WMS inventory transactions, production risk alerts R/Y/G, and Japan head-office monitoring. It explains how the field uses Exa Omni+ around work orders, actual results, and risk signals rather than around complex algorithms.
From First-floor Inbound to the External Finished-goods Warehouse: How Inventory Remains a Company Asset
A real-time inventory transaction synchronization scenario that follows raw materials from first-floor inbound, second-floor IQC inspection, Keeping location management, Picking, process input, and storage in an external 3PL finished-goods warehouse. It explains how field exceptions such as miscellaneous issue, scrap, returns, and stock-count reconciliation are aligned with enterprise inventory accuracy.
The Head-office Screen Is Support, Not Surveillance: A Real-time Control Scenario for the Vietnam Production Subsidiary
A business scenario clarifying how Japan head office introduces Exa Omni+ to synchronize the production, material, quality, inventory, and shipment status of overseas subsidiaries in real time, and to realize proactive support and multinational decision-making rather than passive surveillance. It highlights how multilingual operating infrastructure removes the language barrier among head-office executives, local Japanese managers, and local operators.
A Plant Director’s Day: Judging Delivery, Materials, and Quality Through One Execution Ledger
A business scenario explaining the decision-making value provided by the Exa Omni+ execution ledger, dashboard, Bayesian Risk, Ontology AI-Agent, and Auto-Tuner through the daily scene of a Vietnam production subsidiary executive judging delivery, materials, quality, inventory, and shipment risk.
![BA04-1. [Novel] Probability in Saigon — The Day Data Beat Intuition (Part 1)](/_next/image?url=%2Fstatic%2Fimages%2FBA041-saigon-probability-1.png&w=3840&q=75)
BA04-1. [Novel] Probability in Saigon — The Day Data Beat Intuition (Part 1)
The ultra-high-rise condo pre-sales market in Ho Chi Minh City. A showdown between an intuition-driven ace salesman and a data-driven rookie. This novel format explains how the EXAWin Bayesian engine becomes a tool for victory in the Southeast Asian real estate sales competition. Part 1: The calm before the storm — two salesmen in Saigon.
![BA04-2. [Novel] Probability in Saigon — The Day Data Beat Intuition (Part 2)](/_next/image?url=%2Fstatic%2Fimages%2FBA042-saigon-probability-2.png&w=3840&q=75)
BA04-2. [Novel] Probability in Saigon — The Day Data Beat Intuition (Part 2)
The conclusion of the 480-unit condo pre-sales war in Ho Chi Minh City. President Phan's contract, Tuấn's awakening, and the turnaround led by Park Jun-hyuk's EXAWin. The showdown between intuition and data finally reaches its conclusion.
BA111. Dynamic Buffers and Backward Scheduling: How to Reconfigure the Factory Around Due Dates
This story depicts the process of resolving chronic chaos on the manufacturing floor through EXA's advanced Bayesian algorithm and production scheduling engine. Moving away from the indiscriminate push-style production methods of the past, it introduces data-driven simulation and backward scheduling to precisely control process bottlenecks. Through real-time data learning, the system sets dynamic buffers and reorders priorities toward optimizing schedules based on bottleneck process capability for due-date compliance rather than simple utilization. As a result, by suppressing unnecessary WIP and securing protective capacity, the factory undergoes an innovative transformation in which profitability and due-date hit rate rise even while physical machine operating time decreases. It shows the completed form of a demand-driven Pull production system realized by combining human intuition with cold data computation.
BA024. The Evolution of EXAWin Bayesian Engine: The Day Data Tuned Its Own Parameters
The EXA Bayesian Engine calculated win probabilities, but its precision depended on manually configured initial parameters. When 100 historical deals accumulated, the engine was ready to evolve on its own. Grid Search, MCMC Ensemble Sampling, and Cross-Validation — three mathematical pillars working in concert to find optimal parameters. Told as a story.
BA025. Finding the Optimal Boundary — The Math of Grid Search and Youden's J
How do you find the 'optimal' among 3,240 parameter combinations? Grid Search performs an exhaustive scan, and Youden's J Index finds the balance point between Sensitivity and Specificity. The mathematical principles behind data-driven tuning of sales stage weights (T) and signal sensitivity (k) — the first pillar of Auto-Tuner — explained with business context.
BA026. Consensus of the Particles — The Math of MCMC Ensembles and Cross-Validation
If Grid Search found the 'tallest hill,' the MCMC Ensemble Sampler is the process by which 256 explorers reach consensus that 'the height is correct.' The mathematical principles behind Emcee's affine-invariant walkers, R̂ convergence diagnostics, HDI 95% credible intervals, 5-Fold cross-validation, and Signal Lift analysis — explained with business context.
![[BA03. On-Time Risk: Appendix 1] Anatomy of the EXA Bayesian Engine: Mixture Distributions and Observational Deviation](/_next/image?url=%2Fstatic%2Fimages%2FBA03_1.png&w=3840&q=75)
[BA03. On-Time Risk: Appendix 1] Anatomy of the EXA Bayesian Engine: Mixture Distributions and Observational Deviation
This is the first article in a technical explanation series identifying the operating principles of the EXA engine, which played a major role in the novel-style series [BA03 On-Time Material Inbound: Bayesian MCMC]. Since this series covers Mixture Distributions and MCMC (Markov Chain Monte Carlo) Gibbs Sampling—which are advanced techniques in Bayesian inference—the content may be deep and the calculation process somewhat complex. Therefore, we intend to approach this in a detailed, step-by-step manner to make it as digestible as possible, and it is expected to be a fairly long journey. We recommend reading the original novel first to understand the overall context. Furthermore, as Bayesian theory expands its concepts incrementally, reviewing the episodes and mathematical explanations of BA01 and BA02 beforehand will be much more helpful in grasping this content. The preceding mathematical concepts and logic are being carried forward.
![BA03. [On-Time Material Inbound: Bayesian MCMC] The Real Game in Business is the Fight Against Uncertainty](/_next/image?url=%2Fstatic%2Fimages%2FBA030.png&w=3840&q=75)
BA03. [On-Time Material Inbound: Bayesian MCMC] The Real Game in Business is the Fight Against Uncertainty
BA03. [On-Time Material Inbound: Bayesian MCMC] The Real Game in Business is the Fight Against Uncertainty
![BA02.[Appendix 3] Sales Success Probability Decision System](/_next/image?url=%2Fstatic%2Fimages%2FBA02_imp.png&w=3840&q=75)
BA02.[Appendix 3] Sales Success Probability Decision System
In the previous Parts 1 and 2 of the [BA02. Exa Bayesian Inference: The Invisible Hand of Sales—A 60-Day Gamble] episode, we explored how the Bayesian engine establishes 'prior beliefs' and tracks the trajectory of probabilities through 'signals' and 'silence.' Now, we hold in our hands the pure posterior probability $ P_{raw} $, precisely calculated by the Bayesian parameters α and β. However, it is not over yet. The final decision-making process remains. Even with a 60% probability, the weight of the decision can vary completely depending on whether it was derived from a single meeting or dozens of negotiations.
![BA02.[App. 2] The Paradox of Silence: Entropy and the Geometry of Logarithmic Weighting](/_next/image?url=%2Fstatic%2Fimages%2FBA02_2.png&w=3840&q=75)
BA02.[App. 2] The Paradox of Silence: Entropy and the Geometry of Logarithmic Weighting
BA02.[App. 2] The Paradox of Silence: Entropy and the Geometry of Logarithmic Weighting
![BA02.[Appendix 1] The Bayesian Engine: Mathematical Alchemy for Managing Uncertainty](/_next/image?url=%2Fstatic%2Fimages%2FBA02_1.png&w=3840&q=75)
BA02.[Appendix 1] The Bayesian Engine: Mathematical Alchemy for Managing Uncertainty
This article explains the mathematical principles and effectiveness of the Bayesian engine covered in the [BA02 Episode]. The goal is to precisely predict sales success probabilities in an uncertain business environment. At its core, it addresses the process of deriving optimal decision-making indicators by combining the Beta distribution, which quantifies past experiences, and the Binomial distribution, which captures real-time signals from the field. In particular, it emphasizes maximizing the system’s real-time performance and computational efficiency by utilizing Conjugate Prior distributions, which allow for immediate updates without complex calculations. Furthermore, this model adopts a Recursive Estimation method that makes immediate judgments whenever data occurs, securing technical validity optimized for modern business. Consequently, this document clearly demonstrates how sophisticated mathematical modeling transforms vague intuition into reliable, data-driven insights.
![BA02.[CRM Bayesian Engine] The Invisible Hand: A 60-Day Gamble](/_next/image?url=%2Fstatic%2Fimages%2FBA022.png&w=3840&q=75)
BA02.[CRM Bayesian Engine] The Invisible Hand: A 60-Day Gamble
BA02.[CRM Bayesian Engine] The Invisible Hand: A 60-Day Gamble
![BA01. [Mathematical Breakdown] The Short Shot](/_next/image?url=%2Fstatic%2Fimages%2FBA012.png&w=3840&q=75)
BA01. [Mathematical Breakdown] The Short Shot
BA01. [Mathematical Breakdown] The Short Shot
![BA01.[Bayesian Data Noir] Silent Factory, The Aesthetics of Bayes Sculpting the Truth](/_next/image?url=%2Fstatic%2Fimages%2Fba01_cover.png&w=3840&q=75)
BA01.[Bayesian Data Noir] Silent Factory, The Aesthetics of Bayes Sculpting the Truth
Quantifying the realm of intuition: A case study of dynamic decision-making using Bayesian updates. How does data become a weapon for decision-making in a manufacturing site ruled by uncertainty? This article vividly shows a real-world application of Bayesian statistics through the process of resolving 'Short Shot' defects in an injection molding factory.
![BA04-5. [Series Part 4/Final] Bayesian A/B Testing — Which Sales Strategy is More Effective?](/_next/image?url=%2Fstatic%2Fimages%2FBA045-ab-testing.png&w=3840&q=75)
BA04-5. [Series Part 4/Final] Bayesian A/B Testing — Which Sales Strategy is More Effective?
Email vs. Phone call, Technical demo vs. Business meeting, Discount offer vs. Value proposition — Comparing the effectiveness of sales strategies in real-time using Bayesian probabilities instead of frequentist p-values. Even automating strategy optimization utilizing Thompson Sampling.
![BA04-4. [Series Part 3] Competitive Analysis through Conditional Probability — Knowing the Enemy Reveals the Win Rate](/_next/image?url=%2Fstatic%2Fimages%2FBA044-competitive-analysis.png&w=3840&q=75)
BA04-4. [Series Part 3] Competitive Analysis through Conditional Probability — Knowing the Enemy Reveals the Win Rate
How does the presence of competitors affect our P(Win)? A methodology for mathematically analyzing competitive landscapes and designing strategic response scenarios using conditional probability, Bayesian networks, and the Competition Impact Factor.
![BA04-3. [Series Part 2] Portfolio Probability Management — Reading the Entire Pipeline with Bayes](/_next/image?url=%2Fstatic%2Fimages%2FBA043-portfolio-management.png&w=3840&q=75)
BA04-3. [Series Part 2] Portfolio Probability Management — Reading the Entire Pipeline with Bayes
Beyond the P(Win) of individual deals, we calculate the expected revenue of the entire sales pipeline using Bayes. Conservative/optimistic forecasts, deal priority matrices, and optimal resource allocation — the mathematics and strategy of Bayesian portfolio management.