diff --git a/backend/app/services/analytics_queries.py b/backend/app/services/analytics_queries.py
index 2f9a939e..05fee0da 100644
--- a/backend/app/services/analytics_queries.py
+++ b/backend/app/services/analytics_queries.py
@@ -1095,6 +1095,186 @@ def _velocity_baseline(
}
+def _district_market_saturation(db: Session, *, district_name: str) -> tuple[float | None, int]:
+ """Median sold% активных строящихся ЖК в районе. >50% = зрелый рынок
+ (конкуренты много продали, новый проект имеет место). <20% = свежий
+ (много инвентаря на продажу, сложнее пробиться).
+
+ Возвращает (median_pct, n_objects). None если <5 ЖК с perc.
+ """
+ row = (
+ db.execute(
+ text(
+ """
+ SELECT PERCENTILE_CONT(0.5) WITHIN GROUP (ORDER BY a.perc) AS sold_median,
+ COUNT(*) AS n
+ FROM domrf_kn_sales_agg a
+ JOIN domrf_kn_objects o
+ ON o.obj_id = a.obj_id
+ AND o.snapshot_date = a.snapshot_date
+ WHERE a.type = 'apartments'
+ AND a.perc IS NOT NULL
+ AND o.district_name = :dn
+ AND o.site_status = 'Строящиеся'
+ """
+ ),
+ {"dn": district_name},
+ )
+ .mappings()
+ .first()
+ )
+ if not row or (row["n"] or 0) < 5:
+ return None, int(row["n"] or 0) if row else 0
+ return _f(row["sold_median"]), int(row["n"])
+
+
+def _district_velocity_trend(db: Session, *, district_name: str) -> tuple[float | None, int, int]:
+ """Ratio realised: recent_6mo / prior_6mo. >1.5 — рынок горит, <0.7 —
+ остывает. Считаем за окно 12 мес: H1 2025 vs H2 2025+.
+
+ Возвращает (ratio, recent_units, prior_units). None если данных мало.
+ """
+ row = (
+ db.execute(
+ text(
+ """
+ SELECT
+ SUM(sg.realised) FILTER (WHERE sg.report_month >= DATE '2025-07-01')
+ AS recent,
+ SUM(sg.realised) FILTER (WHERE sg.report_month BETWEEN DATE '2025-01-01'
+ AND DATE '2025-06-30')
+ AS prior
+ FROM domrf_kn_sale_graph sg
+ JOIN domrf_kn_objects o
+ ON o.obj_id = sg.obj_id
+ AND o.snapshot_date = sg.snapshot_date
+ WHERE sg.type = 'apartments'
+ AND o.district_name = :dn
+ """
+ ),
+ {"dn": district_name},
+ )
+ .mappings()
+ .first()
+ )
+ recent = int(row["recent"] or 0) if row else 0
+ prior = int(row["prior"] or 0) if row else 0
+ if prior > 0 and recent > 0:
+ return recent / prior, recent, prior
+ return None, recent, prior
+
+
+_POI_WEIGHTS = {
+ "Транспорт": 1.5,
+ "Метро": 2.0,
+ "Образование": 1.2,
+ "Медицина": 1.3,
+ "Спорт": 1.0,
+ "Продукты": 0.8,
+ "Развлечения": 0.7,
+ "Новостройки": 0.0, # сами ЖК — не используем как amenity
+}
+
+
+def _district_poi_score(db: Session, *, district_name: str) -> float | None:
+ """Среднее по ЖК района: weighted POI count в радиусе 1000м.
+ Используем категории-веса (метро/медицина важнее, новостройки игнор).
+
+ Возвращает None если в районе <3 ЖК с POI.
+ """
+ weights_sql = " ".join(
+ [f"WHEN i.poi_category = '{cat}' THEN {w:.2f}" for cat, w in _POI_WEIGHTS.items()]
+ )
+ row = (
+ db.execute(
+ text(
+ f"""
+ WITH per_obj AS (
+ SELECT i.obj_id,
+ SUM(CASE {weights_sql} ELSE 0.5 END)
+ FILTER (WHERE i.distance_m IS NULL OR i.distance_m <= 1000)
+ AS weighted_poi
+ FROM domrf_kn_infrastructure i
+ JOIN domrf_kn_objects o
+ ON o.obj_id = i.obj_id
+ AND o.snapshot_date = i.snapshot_date
+ WHERE o.district_name = :dn
+ GROUP BY i.obj_id
+ )
+ SELECT AVG(weighted_poi) AS avg_score, COUNT(*) AS n
+ FROM per_obj
+ WHERE weighted_poi > 0
+ """
+ ),
+ {"dn": district_name},
+ )
+ .mappings()
+ .first()
+ )
+ if not row or (row["n"] or 0) < 3:
+ return None
+ return _f(row["avg_score"])
+
+
+def _city_avg_poi_score(db: Session, *, region_code: int = 66) -> float | None:
+ """Средний POI score по всему ЕКБ — для нормировки district_poi_score."""
+ weights_sql = " ".join(
+ [f"WHEN i.poi_category = '{cat}' THEN {w:.2f}" for cat, w in _POI_WEIGHTS.items()]
+ )
+ row = (
+ db.execute(
+ text(
+ f"""
+ WITH per_obj AS (
+ SELECT i.obj_id,
+ SUM(CASE {weights_sql} ELSE 0.5 END)
+ FILTER (WHERE i.distance_m IS NULL OR i.distance_m <= 1000)
+ AS weighted_poi
+ FROM domrf_kn_infrastructure i
+ JOIN domrf_kn_objects o
+ ON o.obj_id = i.obj_id
+ AND o.snapshot_date = i.snapshot_date
+ WHERE o.region_cd = :rc
+ AND o.district_name IS NOT NULL
+ GROUP BY i.obj_id
+ )
+ SELECT AVG(weighted_poi) AS avg_score
+ FROM per_obj
+ WHERE weighted_poi > 0
+ """
+ ),
+ {"rc": region_code},
+ )
+ .mappings()
+ .first()
+ )
+ return _f(row["avg_score"]) if row else None
+
+
+def _current_mortgage_rate(db: Session) -> tuple[float | None, str | None]:
+ """Последняя средневзвешенная ипотечная ставка из cbr_mortgage_series.
+ Возвращает (rate_pct, period_label)."""
+ row = (
+ db.execute(
+ text(
+ """
+ SELECT value, period
+ FROM cbr_mortgage_series
+ WHERE title ILIKE '%ипотечн%жилищн%'
+ AND value IS NOT NULL
+ ORDER BY period DESC
+ LIMIT 1
+ """
+ )
+ )
+ .mappings()
+ .first()
+ )
+ if not row:
+ return None, None
+ return _f(row["value"]), row["period"]
+
+
def _active_competitors_count(
db: Session,
*,
@@ -1289,34 +1469,52 @@ def recommend_mix(
else 1.0
)
- # 3) Class multiplier from yandex_realty_zk price ranges (price_from)
+ # 3) Class multiplier через yandex_realty_zk + Comfort как BASELINE (×1.0).
+ # Раньше делили class_avg/overall_avg где overall = смесь по 12 rows
+ # → числа абсурдные (Elite ×1.22, Comfort+ ×0.66 < Comfort).
+ # Теперь: ratio(class) = class_price_avg / comfort_price_avg.
+ # Реалистичные индустриальные значения: Comfort=1.0, Comfort+=1.02,
+ # Business=1.86, Elite=4.27 (на основе текущих 12 rows yandex_realty_zk).
+ # yandex_realty_class_prices игнорируем — midpoint бессмыслен (ширина
+ # диапазонов класса искажает result).
+ # UI шлёт 'Comfort'/'Comfort+'/'Business'/'Elite' → realty_zk: 'COMFORT'/
+ # 'COMFORT_PLUS'/'BUSINESS'/'ELITE'.
class_multiplier = 1.0
+ class_multiplier_source: str | None = None
if target_class:
- cls_row = (
- db.execute(
- text(
- """
+ zk_norm = {
+ "Comfort": "COMFORT",
+ "Comfort+": "COMFORT_PLUS",
+ "Business": "BUSINESS",
+ "Elite": "ELITE",
+ }.get(target_class)
+ if zk_norm:
+ r = (
+ db.execute(
+ text(
+ """
SELECT
- AVG(price_from) FILTER (WHERE obj_class = :cls) AS class_avg,
- AVG(price_from) AS overall_avg
+ AVG(price_from) FILTER (WHERE obj_class = :cls) AS class_avg,
+ AVG(price_from) FILTER (WHERE obj_class = 'COMFORT') AS comfort_avg
FROM yandex_realty_zk
WHERE price_from IS NOT NULL AND price_from > 0
"""
- ),
- {"cls": target_class},
- )
- .mappings()
- .first()
- )
- cavg = _f(cls_row["class_avg"]) if cls_row else None
- oavg = _f(cls_row["overall_avg"]) if cls_row else None
- if cavg and oavg and oavg > 0:
- class_multiplier = cavg / oavg
- else:
- warnings.append(
- f"Нет ценовых данных yandex_realty_zk для класса '{target_class}',"
- " коэффициент класса = 1.0"
+ ),
+ {"cls": zk_norm},
+ )
+ .mappings()
+ .first()
)
+ cavg = _f(r["class_avg"]) if r else None
+ comfort_avg = _f(r["comfort_avg"]) if r else None
+ if cavg and comfort_avg and comfort_avg > 0:
+ class_multiplier = cavg / comfort_avg
+ class_multiplier_source = "realty_zk_vs_comfort"
+ else:
+ warnings.append(
+ f"Нет ценовых данных yandex_realty_zk для класса '{target_class}'"
+ " — коэффициент класса = 1.0"
+ )
# 4) Bucket distribution from rosreestr_deals — city-wide, last N months.
# Если в каком-либо бакете <30 сделок и окно < 24 мес, расширяем до 24 мес
@@ -1484,26 +1682,57 @@ def recommend_mix(
for r in bucket_rows
}
+ # 5b-2.5) Дополнительные district-specific signals (Tier 2):
+ # sat_factor — насколько зрелый рынок района (median sold% активных
+ # ЖК). >50% = зрелый, новый проект имеет место, +bonus.
+ # <20% = свежий, много инвентаря, -penalty.
+ # trend_factor — recent_6mo / prior_6mo realised. Clamp 0.7..2.0 чтобы
+ # экстремум не разрушал расчёты.
+ # poi_factor — weighted POI density района / city avg. ±5% на цены.
+ sat_median, sat_n = _district_market_saturation(db, district_name=district_row["district_name"])
+ sat_factor = 1 + (sat_median - 50) / 100 * 0.3 if sat_median is not None else 1.0
+
+ trend_ratio, trend_recent, trend_prior = _district_velocity_trend(
+ db, district_name=district_row["district_name"]
+ )
+ trend_factor = max(0.7, min(2.0, trend_ratio)) if trend_ratio else 1.0
+
+ poi_score = _district_poi_score(db, district_name=district_row["district_name"])
+ city_avg_poi = _city_avg_poi_score(db, region_code=region_code)
+ poi_factor = (
+ 1 + (poi_score - city_avg_poi) / max(city_avg_poi, 1) * 0.05
+ if (poi_score is not None and city_avg_poi is not None and city_avg_poi > 0)
+ else 1.0
+ )
+
+ mortgage_rate, mortgage_period = _current_mortgage_rate(db)
+
# 5b-3) Per-bucket project velocity at price_factor=1.0:
# bucket_market_v = темп РЫНКА для bucket'а (deals/mo по всему региону)
- # normalisation = sqrt(N_competitors) — компромисс между
- # «монополист» (÷1) и «равный pie-split» (÷N).
- # Реально продажи распределены по power-law: top-20%
- # ЖК делают 80% сделок, поэтому linear ÷N даёт
- # абсурдные сроки в десятилетия. sqrt — стандартный
- # proxy для "effective competitors" в подобных
- # зашумлённых market-share моделях.
- # project_velocity = bucket_market_v / sqrt(N_competitors)
+ # normalisation = sqrt(N_competitors) — power-law эффективные
+ # конкуренты (sqrt компромисс между ÷1 и ÷N).
+ # project_velocity = bucket_market_v / sqrt(N) × sat_factor × trend_factor
+ # sat — зрелый рынок ускоряет; trend — текущая
+ # динамика (горит/остывает).
# adjusted = project_velocity × price_factor^elasticity
# months_to_sellout = units_planned / adjusted
+ # Цена тоже корректируется на poi_factor (развитость района = премиум).
pf_pow = price_factor**elasticity if price_factor > 0 else 1.0
competitors_norm = math.sqrt(max(competitors, 1))
+ macro_velocity_mult = sat_factor * trend_factor
total_units = 0
for b in buckets:
bucket_market_v = bucket_market_velocities.get(b["bucket"], 0.0)
- bucket_velocity = round(bucket_market_v / competitors_norm, 4)
+ bucket_velocity = round(bucket_market_v / competitors_norm * macro_velocity_mult, 4)
b["velocity_per_month"] = bucket_velocity
+ # POI-корректировка на цену (на ВСЕ p25/median/p75)
+ b["price_median_per_m2"] = round(b["price_median_per_m2"] * poi_factor, 2)
+ b["price_p25_per_m2"] = round(b["price_p25_per_m2"] * poi_factor, 2)
+ b["price_p75_per_m2"] = round(b["price_p75_per_m2"] * poi_factor, 2)
if b["units_planned"] and bucket_velocity > 0:
+ # Revenue тоже пересчитываем после POI-correction (linear scale).
+ if b["revenue_planned_rub"] is not None:
+ b["revenue_planned_rub"] = round(b["revenue_planned_rub"] * poi_factor, 2)
adjusted_velocity = bucket_velocity * pf_pow
b["months_to_sellout"] = (
round(b["units_planned"] / adjusted_velocity, 1) if adjusted_velocity > 0 else None
@@ -1511,6 +1740,11 @@ def recommend_mix(
total_units += b["units_planned"]
else:
b["months_to_sellout"] = None
+ # Итог revenue + weighted_avg_price после POI-correction (linear scale).
+ if have_revenue:
+ total_revenue *= poi_factor
+ if weighted_avg_price is not None:
+ weighted_avg_price = round(weighted_avg_price * poi_factor, 2)
# 5c) Inverse mode: target_months → required price_factor.
# required_velocity = total_units / target_months
@@ -1617,6 +1851,7 @@ def recommend_mix(
"district_median_price_per_m2": district_median,
"district_factor": round(district_factor, 4),
"class_multiplier": round(class_multiplier, 4),
+ "class_multiplier_source": class_multiplier_source,
"target_class": target_class,
"months_window": months_window,
"effective_window_months": effective_window,
@@ -1630,6 +1865,18 @@ def recommend_mix(
"velocity_objects": vel["objects_count"],
"competitors_count": competitors,
"competitors_scope": competitors_scope,
+ "saturation_median": sat_median,
+ "saturation_n": sat_n,
+ "sat_factor": round(sat_factor, 4),
+ "velocity_trend_ratio": (round(trend_ratio, 2) if trend_ratio is not None else None),
+ "trend_recent_units": trend_recent,
+ "trend_prior_units": trend_prior,
+ "trend_factor": round(trend_factor, 4),
+ "poi_score": round(poi_score, 1) if poi_score is not None else None,
+ "poi_score_city_avg": (round(city_avg_poi, 1) if city_avg_poi is not None else None),
+ "poi_factor": round(poi_factor, 4),
+ "mortgage_rate_pct": mortgage_rate,
+ "mortgage_rate_period": mortgage_period,
"elasticity": elasticity,
"elasticity_r2": elast["r2"],
"elasticity_n": elast["n"],
diff --git a/frontend/src/app/analytics/recommend/page.tsx b/frontend/src/app/analytics/recommend/page.tsx
index 065a68bf..b2a6c316 100644
--- a/frontend/src/app/analytics/recommend/page.tsx
+++ b/frontend/src/app/analytics/recommend/page.tsx
@@ -153,14 +153,35 @@ export default function RecommendPage() {
lineHeight: 1.4,
}}
>
- 💼 «{data.scope.district}
- {data.scope.target_class
- ? ` · ${data.scope.target_class}`
- : ""}
- {input.area_total_m2
- ? ` · ${input.area_total_m2.toLocaleString("ru")} м²`
- : ""}
- »: {data.summary.headline}
+
+ 💼 «{data.scope.district}
+ {data.scope.target_class
+ ? ` · ${data.scope.target_class}`
+ : ""}
+ {input.area_total_m2
+ ? ` · ${input.area_total_m2.toLocaleString("ru")} м²`
+ : ""}
+ »: {data.summary.headline}
+
+
+ 📊
+ {data.scope.mortgage_rate_pct != null
+ ? ` Ставка ЦБ ${data.scope.mortgage_rate_pct.toFixed(2)}% (${data.scope.mortgage_rate_period})`
+ : " ставка ЦБ нет данных"}
+ {data.scope.poi_score != null &&
+ data.scope.poi_score_city_avg != null
+ ? ` · POI ${data.scope.poi_score.toFixed(0)}/${data.scope.poi_score_city_avg.toFixed(0)} (${data.scope.poi_score > data.scope.poi_score_city_avg ? "выше" : "ниже"} среднего)`
+ : ""}
+
) : null}
@@ -240,24 +261,43 @@ export default function RecommendPage() {
}
/>
50
+ ? `зрелый рынок (${data.scope.saturation_n} ЖК)`
+ : data.scope.saturation_median < 25
+ ? `свежий, мало распродано (${data.scope.saturation_n} ЖК)`
+ : `умеренная зрелость (${data.scope.saturation_n} ЖК)`
}
/>
1 ? "🚀" : data.scope.velocity_trend_ratio < 0.8 ? "❄" : "→"} ×${data.scope.velocity_trend_ratio.toFixed(2)}`
+ : "—"
}
+ hint={
+ data.scope.velocity_trend_ratio == null
+ ? "нет sale_graph"
+ : data.scope.velocity_trend_ratio > 1.5
+ ? "рынок ускоряется"
+ : data.scope.velocity_trend_ratio < 0.8
+ ? "остывает"
+ : "стабильный"
+ }
+ />
+
diff --git a/frontend/src/components/analytics/RecommendVelocityPanel.tsx b/frontend/src/components/analytics/RecommendVelocityPanel.tsx
index 35723614..96cd0406 100644
--- a/frontend/src/components/analytics/RecommendVelocityPanel.tsx
+++ b/frontend/src/components/analytics/RecommendVelocityPanel.tsx
@@ -264,8 +264,18 @@ export function RecommendVelocityPanel({
? `sale_graph: ${scope.velocity_objects} ЖК / ${scope.velocity_observations} точек`
: "fallback на rosreestr-сделки"}
), нормирован на {scope.competitors_count} активных
- конкурентов в районе ). При price ×{priceFactor.toFixed(2)} темп =
- базовый × {priceFactor.toFixed(2)}^{elasticity} = ×{pfPow.toFixed(3)}.
+ конкурентов в районе. Применены macro-факторы:{" "}
+ sat ×{scope.sat_factor.toFixed(2)}
+ {scope.saturation_median != null
+ ? ` (sold% ${scope.saturation_median.toFixed(0)})`
+ : ""}{" "}
+ · trend ×{scope.trend_factor.toFixed(2)}
+ {scope.velocity_trend_ratio != null
+ ? ` (raw ×${scope.velocity_trend_ratio.toFixed(2)} clamp 0.7..2.0)`
+ : ""}{" "}
+ · POI ×{scope.poi_factor.toFixed(2)} (на цену) ). При
+ price ×{priceFactor.toFixed(2)} темп = базовый ×{" "}
+ {priceFactor.toFixed(2)}^{elasticity} = ×{pfPow.toFixed(3)}.
);
diff --git a/frontend/src/types/analytics.ts b/frontend/src/types/analytics.ts
index 711f26e9..17dcf7f5 100644
--- a/frontend/src/types/analytics.ts
+++ b/frontend/src/types/analytics.ts
@@ -239,6 +239,7 @@ export interface RecommendMixOutput {
district_factor: number;
class_multiplier: number;
target_class: string | null;
+ class_multiplier_source: "realty_zk_vs_comfort" | null;
months_window: number;
effective_window_months: number;
region_code: number;
@@ -253,6 +254,18 @@ export interface RecommendMixOutput {
| "district"
| "region"
| "fallback_singleton";
+ saturation_median: number | null;
+ saturation_n: number;
+ sat_factor: number;
+ velocity_trend_ratio: number | null;
+ trend_recent_units: number;
+ trend_prior_units: number;
+ trend_factor: number;
+ poi_score: number | null;
+ poi_score_city_avg: number | null;
+ poi_factor: number;
+ mortgage_rate_pct: number | null;
+ mortgage_rate_period: string | null;
elasticity: number;
elasticity_r2: number;
elasticity_n: number;