Urban Rental Market Intelligence — NYC

Deep-dive analysis of 50,000+ Airbnb listings across New York City. Borough pricing intelligence, neighborhood clustering, review patterns, budget optimizer, and interactive Folium maps across 5 boroughs and 200+ neighborhoods. Includes a tier-based pricing recommender scored against the full listing set.

ⓘProject description and metrics shown here are representative — drawn from a real engagement, with the client name anonymized where confidentiality applies.

Real estate investors and hosts lacked granular, data-driven insights into NYC's short-term rental market. Pricing decisions were based on intuition rather than market intelligence, leaving significant revenue on the table.

We performed a deep-dive analysis of 50,000+ Airbnb listings across all 5 NYC boroughs. The platform includes borough-level pricing intelligence, neighborhood clustering via K-Means, review sentiment patterns, a budget optimizer tool, and interactive Folium maps covering 200+ neighborhoods.

# K-Means neighborhood clustering for pricing tiers
from sklearn.cluster import KMeans
from sklearn.preprocessing import StandardScaler

def cluster_neighborhoods(df, n_clusters=5):
    """Segment neighborhoods by price/review patterns."""
    features = df[['price', 'reviews_per_month',
                    'availability_365', 'minimum_nights']]

    scaler = StandardScaler()
    X = scaler.fit_transform(features.fillna(0))

    kmeans = KMeans(n_clusters=n_clusters, random_state=42)
    df['price_tier'] = kmeans.fit_predict(X)

    # Tier feeds the neighborhood map and the budget
    # optimizer, which ranks areas against a user's rate
    return df

K-Means segments 50K+ listings into five price tiers from price, review velocity, availability and minimum-stay features. The platform maps those tiers across 200+ neighborhoods in all 5 boroughs, alongside a budget optimizer that ranks neighborhoods against a nightly rate the visitor sets.