brackt/app/services/simulations/nba-simulator.ts

/**
 * NBA Playoff Simulator
 *
 * Monte Carlo simulation of the NBA playoffs including seeding projection
 * for the current season (2025-26).
 *
 * Algorithm:
 *   1. Load all participants for the sports season from DB
 *   2. Match participant names to hardcoded team data (Elo + seed probabilities)
 *   3. For each simulation:
 *      a. Assign each team a seed based on its weighted probability distribution (p_1..p_10)
 *         Teams with no seed probabilities always miss the playoffs (seed = 11)
 *      b. Sort each conference by drawn seed + random tiebreaker
 *         → Top 6 lock in directly; seeds 7–10 enter the Play-In tournament
 *      c. Simulate Play-In (single game each):
 *         - Game 1: seed 7 vs seed 8 → winner becomes 7th playoff seed
 *         - Game 2: seed 9 vs seed 10 → winner advances
 *         - Game 3: Game 1 loser vs Game 2 winner → winner becomes 8th playoff seed
 *      d. Simulate NBA playoff bracket (best-of-7 series each round):
 *         Round 1:     1v8, 4v5, 2v7, 3v6  (per conference)
 *         Round 2:     Conference Semis (winners of 1v8/4v5, winners of 2v7/3v6)
 *         Round 3:     Conference Finals
 *         NBA Finals:  East champion vs West champion
 *   4. Track placement counts per scoring tier
 *   5. Convert counts to probability distributions
 *
 * Win probability (Elo, PARITY_FACTOR = 400):
 *   P(A beats B) = 1 / (1 + 10^((eloB - eloA) / 400))
 *
 * Placement tiers → SimulationProbabilities mapping:
 *   probFirst         = NBA champion (1 per sim)
 *   probSecond        = NBA Finals loser (1 per sim)
 *   probThird/Fourth  = Conference Finals losers (2 per sim — East + West)
 *   probFifth–Eighth  = Conference Semis losers (4 per sim)
 *   Round 1 losers    → all 0 (score 0 points)
 *   Missed playoffs   → all 0
 *
 * Elo ratings and seed probabilities are hardcoded below (March 2026 data).
 * Source: Basketball-Reference Playoff Probabilities + Neil Paine Substack estimates.
 * Update at the start of each season.
 */

import { database } from "~/database/context";
import { eq } from "drizzle-orm";
import * as schema from "~/database/schema";
import type { Simulator, SimulationResult } from "./types";
import { normalizeTeamName } from "~/lib/normalize-team-name";

// ─── Simulation parameters ────────────────────────────────────────────────────

const NUM_SIMULATIONS = 50_000;

/**
 * Elo parity factor. NBA uses 400 (standard formula).
 * A 400-point Elo difference → ~90.9% win probability per game.
 */
const PARITY_FACTOR = 400;

/** Seed probability keys — ordered p_1..p_10 for the drawSeed() inner loop. */
const SEED_KEYS = ["p_1", "p_2", "p_3", "p_4", "p_5", "p_6", "p_7", "p_8", "p_9", "p_10"] as const;

// ─── Team data (2025-26 season, as of March 6, 2026) ─────────────────────────
//
// elo:  Estimated Elo rating (higher = stronger).
// p_1 through p_10: Probability of finishing at each conference seed.
//   Sum of all p_X for a team = probability of making the playoffs.
//   Teams with no p_X entries always miss the playoffs in simulation.
//
// Sources:
//   - Elo: Playoff rating (last 110 games, no regression to mean, postseason games 3× weight).
//          This is the appropriate signal for simulating playoff matchups.
//   - Seed probs: Basketball-Reference Playoff Probabilities Report (March 16, 2026).
//
// Seed probability methodology:
//   BBRef reports conditional seed probabilities (summing to ~100% per team).
//   We scale each team's values by their Playoffs% to get unconditional probabilities.
//   The drawSeed() function then treats the remainder (1 - sum) as "miss playoffs".
//   Formula: p_X = (BBRef_conditional_X / 100) × (Playoffs% / 100)

interface NbaTeamData {
  conference: "Eastern" | "Western";
  elo: number;
  p_1?: number;
  p_2?: number;
  p_3?: number;
  p_4?: number;
  p_5?: number;
  p_6?: number;
  p_7?: number;
  p_8?: number;
  p_9?: number;
  p_10?: number;
}

const TEAMS_DATA: Record<string, NbaTeamData> = {
  // ── Eastern Conference ──────────────────────────────────────────────────────
  // Elo = playoff rating (last 110 games, no regression, postseason games 3× weight)
  // Seed probs = BBRef conditional × (Playoffs% / 100)

  // Detroit (PO%=100%): locked as 1-seed
  "Detroit Pistons": { conference: "Eastern", elo: 1558,
    p_1: 0.982, p_2: 0.016, p_3: 0.001 },

  // Boston (PO%=100%): clear 2/3 seed
  "Boston Celtics": { conference: "Eastern", elo: 1699,
    p_1: 0.014, p_2: 0.540, p_3: 0.389, p_4: 0.052, p_5: 0.004 },

  // New York (PO%=100%)
  "New York Knicks": { conference: "Eastern", elo: 1626,
    p_1: 0.003, p_2: 0.423, p_3: 0.479, p_4: 0.086, p_5: 0.009, p_6: 0.001 },

  // Cleveland (PO%=99.9%): mostly 4-seed, slight play-in risk
  "Cleveland Cavaliers": { conference: "Eastern", elo: 1628,
    p_2: 0.020, p_3: 0.117, p_4: 0.684, p_5: 0.137, p_6: 0.032, p_7: 0.009, p_8: 0.001 },

  // Orlando (PO%=88.8%): 5/6-seed range, play-in risk
  "Orlando Magic": { conference: "Eastern", elo: 1508,
    p_3: 0.007, p_4: 0.075, p_5: 0.333, p_6: 0.182, p_7: 0.139, p_8: 0.091, p_9: 0.044, p_10: 0.018 },

  // Miami (PO%=78.7%)
  "Miami Heat": { conference: "Eastern", elo: 1530,
    p_3: 0.004, p_4: 0.041, p_5: 0.212, p_6: 0.224, p_7: 0.255, p_8: 0.113, p_9: 0.037, p_10: 0.009 },

  // Toronto (PO%=86.4%)
  "Toronto Raptors": { conference: "Eastern", elo: 1467,
    p_3: 0.001, p_4: 0.038, p_5: 0.165, p_6: 0.324, p_7: 0.192, p_8: 0.103, p_9: 0.041, p_10: 0.011 },

  // Atlanta (PO%=46.7%): mostly play-in range
  "Atlanta Hawks": { conference: "Eastern", elo: 1496,
    p_4: 0.001, p_5: 0.011, p_6: 0.022, p_7: 0.058, p_8: 0.124, p_9: 0.134, p_10: 0.123 },

  // Philadelphia (PO%=52.9%)
  "Philadelphia 76ers": { conference: "Eastern", elo: 1471,
    p_5: 0.011, p_6: 0.039, p_7: 0.079, p_8: 0.116, p_9: 0.134, p_10: 0.091 },

  // Charlotte (PO%=47.1%): deep play-in territory
  "Charlotte Hornets": { conference: "Eastern", elo: 1496,
    p_5: 0.002, p_6: 0.004, p_7: 0.017, p_8: 0.058, p_9: 0.118, p_10: 0.201 },

  // Milwaukee (PO%=0%)
  "Milwaukee Bucks": { conference: "Eastern", elo: 1442 },

  // Chicago (PO%=0%)
  "Chicago Bulls": { conference: "Eastern", elo: 1381 },

  // Brooklyn (PO%=0%)
  "Brooklyn Nets": { conference: "Eastern", elo: 1334 },

  // Indiana (PO%=0%)
  "Indiana Pacers": { conference: "Eastern", elo: 1433 },

  // Washington (PO%=0%)
  "Washington Wizards": { conference: "Eastern", elo: 1255 },

  // ── Western Conference ──────────────────────────────────────────────────────

  // OKC (PO%=100%): dominant 1-seed
  "Oklahoma City Thunder": { conference: "Western", elo: 1731,
    p_1: 0.920, p_2: 0.081 },

  // San Antonio (PO%=100%): locked as 2-seed
  "San Antonio Spurs": { conference: "Western", elo: 1599,
    p_1: 0.081, p_2: 0.919 },

  // Houston (PO%=99.8%): 3/4 seed range
  "Houston Rockets": { conference: "Western", elo: 1564,
    p_3: 0.467, p_4: 0.258, p_5: 0.169, p_6: 0.092, p_7: 0.014, p_8: 0.001 },

  // Denver (PO%=99.8%)
  "Denver Nuggets": { conference: "Western", elo: 1618,
    p_3: 0.222, p_4: 0.270, p_5: 0.277, p_6: 0.181, p_7: 0.043, p_8: 0.001 },

  // LA Lakers (PO%=99.7%)
  "Los Angeles Lakers": { conference: "Western", elo: 1569,
    p_3: 0.219, p_4: 0.267, p_5: 0.242, p_6: 0.172, p_7: 0.079, p_8: 0.003 },

  // Minnesota (PO%=96.2%)
  "Minnesota Timberwolves": { conference: "Western", elo: 1603,
    p_3: 0.072, p_4: 0.154, p_5: 0.222, p_6: 0.340, p_7: 0.173, p_8: 0.007 },

  // Phoenix (PO%=83.4%): mostly 7-seed play-in entry
  "Phoenix Suns": { conference: "Western", elo: 1500,
    p_3: 0.011, p_4: 0.032, p_5: 0.065, p_6: 0.165, p_7: 0.517, p_8: 0.051, p_9: 0.005 },

  // LA Clippers (PO%=71.1%): heavy play-in range
  "LA Clippers": { conference: "Western", elo: 1573,
    p_6: 0.042, p_7: 0.468, p_8: 0.112, p_9: 0.027 },

  // Golden State (PO%=30.3%): longshot play-in
  "Golden State Warriors": { conference: "Western", elo: 1530,
    p_6: 0.003, p_7: 0.053, p_8: 0.160, p_9: 0.147 },

  // Portland (PO%=19.5%): deep longshot
  "Portland Trail Blazers": { conference: "Western", elo: 1426,
    p_7: 0.013, p_8: 0.077, p_9: 0.111 },

  // Dallas (PO%=0%)
  "Dallas Mavericks": { conference: "Western", elo: 1473 },

  // Memphis (PO%=0%)
  "Memphis Grizzlies": { conference: "Western", elo: 1417 },

  // New Orleans (PO%=0%)
  "New Orleans Pelicans": { conference: "Western", elo: 1380 },

  // Sacramento (PO%=0%)
  "Sacramento Kings": { conference: "Western", elo: 1352 },

  // Utah (PO%=0%)
  "Utah Jazz": { conference: "Western", elo: 1334 },
};

// ─── Public helpers (exported for unit testing) ───────────────────────────────

export { normalizeTeamName };

/** Look up team data by participant name (case-insensitive). */
export function getTeamData(name: string): NbaTeamData | undefined {
  const normalized = normalizeTeamName(name);
  for (const [teamName, data] of Object.entries(TEAMS_DATA)) {
    if (normalizeTeamName(teamName) === normalized) return data;
  }
  return undefined;
}

/**
 * Elo win probability for team A over team B.
 *   P(A) = 1 / (1 + 10^((eloB - eloA) / PARITY_FACTOR))
 * Exported for unit testing.
 */
export function eloWinProbability(eloA: number, eloB: number): number {
  return 1 / (1 + Math.pow(10, (eloB - eloA) / PARITY_FACTOR));
}

// ─── Internal types ───────────────────────────────────────────────────────────

interface TeamEntry {
  id: string;
  name: string;
  data: NbaTeamData | undefined;
}

/** Get Elo for a team entry.
 *  Fallback 1400 = conservative below-average estimate for unknown/unrecognized teams. */
function elo(entry: TeamEntry): number {
  return entry.data?.elo ?? 1400;
}

// ─── Simulator ────────────────────────────────────────────────────────────────

export class NBASimulator implements Simulator {
  async simulate(sportsSeasonId: string): Promise<SimulationResult[]> {
    const db = database();

    // 1. Load all participants for this sports season.
    const participantRows = await db
      .select({ id: schema.participants.id, name: schema.participants.name })
      .from(schema.participants)
      .where(eq(schema.participants.sportsSeasonId, sportsSeasonId));

    if (participantRows.length === 0) {
      throw new Error(
        `No participants found for sports season ${sportsSeasonId}. ` +
          `Add NBA teams as participants before running simulation.`
      );
    }

    // 2. Match participant names to hardcoded team data.
    //    Teams with no match or no seed probabilities will always miss the playoffs.
    const participantIds = participantRows.map((r) => r.id);

    const teams: TeamEntry[] = participantRows.map((r) => ({
      id: r.id,
      name: r.name,
      data: getTeamData(r.name),
    }));

    // Separate by conference for simulation (fall back to Eastern if no data found).
    const easternTeams = teams.filter((t) => (t.data?.conference ?? "Eastern") === "Eastern");
    const westernTeams = teams.filter((t) => t.data?.conference === "Western");

    // Validate: each conference needs at least 10 teams to fill the bracket + play-in.
    if (easternTeams.length < 10 || westernTeams.length < 10) {
      throw new Error(
        `Each conference needs at least 10 participants (got East: ${easternTeams.length}, ` +
          `West: ${westernTeams.length}). Add all 30 NBA teams before running simulation.`
      );
    }

    // ─── Helpers (defined once, outside the hot loop) ─────────────────────────

    /** Draw a conference seed (1–10) based on a team's probability distribution.
     *  Returns 11 if the draw falls outside all p_X values (team misses playoffs). */
    const drawSeed = (entry: TeamEntry): number => {
      const data = entry.data;
      if (!data) return 11; // Unknown team — always misses playoffs
      let r = Math.random();
      for (let i = 0; i < SEED_KEYS.length; i++) {
        const prob = data[SEED_KEYS[i]] ?? 0;
        r -= prob;
        if (r <= 0) return i + 1;
      }
      return 11; // Missed playoffs
    };

    /** Simulate a single playoff game. Returns the winner. */
    const simGame = (a: TeamEntry, b: TeamEntry): TeamEntry =>
      Math.random() < eloWinProbability(elo(a), elo(b)) ? a : b;

    /** Simulate a best-of-7 series. Returns winner and loser. */
    const simSeries = (a: TeamEntry, b: TeamEntry): { winner: TeamEntry; loser: TeamEntry } => {
      const winProb = eloWinProbability(elo(a), elo(b));
      let winsA = 0;
      let winsB = 0;
      while (winsA < 4 && winsB < 4) {
        if (Math.random() < winProb) winsA++; else winsB++;
      }
      return winsA === 4 ? { winner: a, loser: b } : { winner: b, loser: a };
    };

    /** Simulate the Play-In tournament.
     *  @param candidates 4 teams sorted by seeding position [7th, 8th, 9th, 10th]
     *  @returns [7th playoff seed, 8th playoff seed] */
    const simPlayIn = ([s7, s8, s9, s10]: [TeamEntry, TeamEntry, TeamEntry, TeamEntry]): [TeamEntry, TeamEntry] => {
      // Game 1: 7 vs 8 — winner locks up the 7th seed
      const game1Winner = simGame(s7, s8);
      const game1Loser  = game1Winner === s7 ? s8 : s7;
      // Game 2: 9 vs 10 — winner advances to the final play-in game
      const game2Winner = simGame(s9, s10);
      // Game 3: loser of Game 1 vs winner of Game 2 — winner gets the 8th seed
      return [game1Winner, simGame(game1Loser, game2Winner)];
    };

    /** Build an 8-team conference bracket [s1..s8] for one simulation iteration.
     *  Seeds are drawn probabilistically; positions 7–10 go through the Play-In. */
    const buildConferenceBracket = (confTeams: TeamEntry[]): TeamEntry[] => {
      const seeded = confTeams.map((t) => ({
        team: t,
        seed: drawSeed(t),
        tiebreaker: Math.random(),
      }));
      seeded.sort((a, b) => a.seed - b.seed || a.tiebreaker - b.tiebreaker);

      const top6 = seeded.slice(0, 6).map((x) => x.team);
      const playIn = seeded.slice(6, 10).map((x) => x.team) as
        [TeamEntry, TeamEntry, TeamEntry, TeamEntry];
      const [seed7, seed8] = simPlayIn(playIn);
      return [...top6, seed7, seed8];
    };

    /** Round 1: 1v8, 4v5, 2v7, 3v6. Returns 4 winners. */
    const simR1 = ([s1, s2, s3, s4, s5, s6, s7, s8]: TeamEntry[]): TeamEntry[] => [
      simSeries(s1, s8).winner,
      simSeries(s4, s5).winner,
      simSeries(s2, s7).winner,
      simSeries(s3, s6).winner,
    ];

    /** Conference Semis: winner(1v8) vs winner(4v5), winner(2v7) vs winner(3v6). */
    const simR2 = ([w0, w1, w2, w3]: TeamEntry[]): { winners: TeamEntry[]; losers: TeamEntry[] } => {
      const m1 = simSeries(w0, w1);
      const m2 = simSeries(w2, w3);
      return { winners: [m1.winner, m2.winner], losers: [m1.loser, m2.loser] };
    };

    // 3. Integer placement count maps — initialized to 0 for all participants.
    const championCounts       = new Map<string, number>(participantIds.map((id) => [id, 0]));
    const finalistCounts       = new Map<string, number>(participantIds.map((id) => [id, 0]));
    const confFinalLoserCounts = new Map<string, number>(participantIds.map((id) => [id, 0]));
    const confSemiLoserCounts  = new Map<string, number>(participantIds.map((id) => [id, 0]));

    // 4. Monte Carlo simulation loop.
    for (let s = 0; s < NUM_SIMULATIONS; s++) {
      // ── Build brackets ───────────────────────────────────────────────────────
      const eastBracket = buildConferenceBracket(easternTeams);
      const westBracket = buildConferenceBracket(westernTeams);

      // ── Simulate rounds ──────────────────────────────────────────────────────
      const { winners: eastR2Winners, losers: eastR2Losers } = simR2(simR1(eastBracket));
      const { winner: eastChamp, loser: eastCFLoser } = simSeries(eastR2Winners[0], eastR2Winners[1]);

      const { winners: westR2Winners, losers: westR2Losers } = simR2(simR1(westBracket));
      const { winner: westChamp, loser: westCFLoser } = simSeries(westR2Winners[0], westR2Winners[1]);

      const { winner: champion, loser: finalist } = simSeries(eastChamp, westChamp);

      // ── Record counts (maps are pre-populated so .get() is always defined) ───
      championCounts.set(champion.id,      (championCounts.get(champion.id) ?? 0)      + 1);
      finalistCounts.set(finalist.id,      (finalistCounts.get(finalist.id) ?? 0)      + 1);
      confFinalLoserCounts.set(eastCFLoser.id, (confFinalLoserCounts.get(eastCFLoser.id) ?? 0) + 1);
      confFinalLoserCounts.set(westCFLoser.id, (confFinalLoserCounts.get(westCFLoser.id) ?? 0) + 1);
      for (const loser of [...eastR2Losers, ...westR2Losers]) {
        confSemiLoserCounts.set(loser.id, (confSemiLoserCounts.get(loser.id) ?? 0) + 1);
      }
      // Round 1 losers are not counted (0 points per scoring rules).
    }

    // 5. Convert integer counts to probability distributions.
    //    Exact denominators guarantee column sums of 1.0 by construction:
    //      probFirst/Second       → N total (1 per sim)
    //      probThird/Fourth       → confFinalLoserCounts / (2*N)  — 2 conf final losers per sim
    //      probFifth–Eighth       → confSemiLoserCounts  / (4*N)  — 4 conf semi losers per sim
    const N = NUM_SIMULATIONS;
    const results: SimulationResult[] = participantIds.map((participantId) => {
      const c  = championCounts.get(participantId) ?? 0;
      const f  = finalistCounts.get(participantId) ?? 0;
      const cf = confFinalLoserCounts.get(participantId) ?? 0;
      const cs = confSemiLoserCounts.get(participantId) ?? 0;
      return {
        participantId,
        probabilities: {
          probFirst:   c  / N,
          probSecond:  f  / N,
          probThird:   cf / (2 * N),
          probFourth:  cf / (2 * N),
          probFifth:   cs / (4 * N),
          probSixth:   cs / (4 * N),
          probSeventh: cs / (4 * N),
          probEighth:  cs / (4 * N),
        },
        source: "nba_bracket_monte_carlo",
      };
    });

    // 6. Per-position normalization — belt-and-suspenders guard against floating-point
    //    division residuals. Columns are already near-exactly 1.0 after step 5.
    const positionKeys: Array<keyof (typeof results)[0]["probabilities"]> = [
      "probFirst", "probSecond", "probThird", "probFourth",
      "probFifth", "probSixth", "probSeventh", "probEighth",
    ];
    for (const key of positionKeys) {
      const colSum = results.reduce((s, r) => s + r.probabilities[key], 0);
      const residual = 1.0 - colSum;
      if (residual !== 0) {
        const maxResult = results.reduce((best, r) =>
          r.probabilities[key] > best.probabilities[key] ? r : best
        );
        maxResult.probabilities[key] += residual;
      }
    }

    return results;
  }
}