{
  "docId": "019dd923-5de0-76bd-a165-d55b06f0d704",
  "docSlug": "54caeb8307d177cd",
  "documentTitle": "EY Georgia Medicaid Oral",
  "authorId": "proposals",
  "authorName": "EY",
  "documentKindSlug": "consulting-deck",
  "documentKindLabel": "Consulting deck",
  "sourceTypeSlug": "strategy_consulting",
  "sourceTypeLabel": "Strategy consulting",
  "presentationDate": null,
  "orientation": "landscape",
  "aspectRatio": 1.294,
  "pageNumber": 26,
  "pageCount": 33,
  "prevPage": 25,
  "nextPage": 27,
  "slideType": "appendix_methodology",
  "function": "present_framework",
  "density": "dense",
  "nDataPoints": 2,
  "notes": "The slide uses a simple process flow diagram to explain the ML pipeline.",
  "elementsJson": [
    "headline_text",
    "paragraph",
    "process_diagram",
    "numbered_list"
  ],
  "metadataConfidence": 1,
  "imagePath": null,
  "slideHref": "/slides/019dd923-5de0-76bd-a165-d55b06f0d704/26",
  "deckHref": "/decks/019dd923-5de0-76bd-a165-d55b06f0d704",
  "deckJsonHref": "/decks/019dd923-5de0-76bd-a165-d55b06f0d704.json",
  "deckAnchorHref": "/decks/019dd923-5de0-76bd-a165-d55b06f0d704#slide-26",
  "components": [
    {
      "bbox": null,
      "kind": "callout",
      "text": "EY developed machine learning algorithms that improved accuracy by 24% over traditional actuarial models.",
      "attrs": null,
      "subkind": null,
      "toolName": "Visual emphasis",
      "toolSlug": "visual-emphasis",
      "confidence": null,
      "componentId": "019dd951-fef6-7690-9a4c-47409059d51a",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.45,
        "w": 0.82,
        "x": 0.09,
        "y": 0.29
      },
      "kind": "diagram",
      "text": "Input dataset -> Machine learning algorithm -> Output for decision making",
      "attrs": null,
      "subkind": "process",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "175828f7-a763-406e-83ca-2af42789ff39",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.06,
        "w": 0.82,
        "x": 0.09,
        "y": 0.238
      },
      "kind": "framework",
      "text": "Example Methodology: Estimating medical cost",
      "attrs": null,
      "subkind": "instance",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "8dec99c8-94dc-4ebf-989d-d7dd308472f1",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.12,
        "w": 0.65,
        "x": 0.26,
        "y": 0.75
      },
      "kind": "list",
      "text": "1. EY developed machine learning algorithms that improved accuracy by 24% over traditional actuarial models\n2. Input data included disease specific variables for 5 of the highest cost conditions",
      "attrs": null,
      "subkind": "bullet",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "259a2bd4-b0e6-4058-96be-5e868195254e",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": null,
      "kind": "metric",
      "text": "accuracy improvement: 24%",
      "attrs": null,
      "subkind": "primary",
      "toolName": "Quantification",
      "toolSlug": "quantification",
      "confidence": null,
      "componentId": "019dd951-fef6-7690-9a4c-4a07e452e15f",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.03,
        "w": 0.6,
        "x": 0.09,
        "y": 0.18
      },
      "kind": "paragraph",
      "text": "EY has capabilities to work with claims data to improve actuarial forecasts",
      "attrs": null,
      "subkind": "paragraph",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "296da3d5-966b-452a-99a2-0b07dbf17346",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.04,
        "w": 0.35,
        "x": 0.09,
        "y": 0.08
      },
      "kind": "title",
      "text": "Analytics and machine learning",
      "attrs": null,
      "subkind": "headline",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "cdef22d3-2183-4d1d-a023-22a7861863c2",
      "frameworkName": null,
      "frameworkSlug": null
    }
  ],
  "metrics": [],
  "tools": [],
  "frameworks": [
    {
      "name": "process",
      "slug": null,
      "matchId": "99f34d74-b9c7-4e8b-a3f4-7c434cfdd219",
      "evidence": "The slide depicts a linear flow from input to algorithm to output.",
      "confidence": 0.9
    }
  ],
  "arcBeats": [
    {
      "to": 33,
      "from": 25,
      "beatId": "53413b3d-08a0-4284-bd78-bc5bc4f74d12",
      "arcName": "The Consultant's Gambit",
      "arcSlug": "consultants-gambit",
      "beatName": "Impact & Next Steps",
      "beatSlug": "consultants-gambit-impact-next-steps",
      "evidence": "The deck concludes with a discussion of the impact of EY's consulting services and next steps.",
      "position": 4,
      "confidence": 0.8,
      "parentBeatName": "Resolution",
      "parentBeatSlug": "resolution"
    }
  ],
  "loops": [],
  "imagePathAlt": null,
  "thumbSrc": null,
  "thumbSrcAlt": null,
  "locked": true
}