Skip to content
TheChatArchiveThe Chat Archive
Claudeclaude-opus-4-20250514· AnthropicHugging Face LMArena Human Preference 140K

give me an data set with 1000 rows simulating actual data with these variables Liquidity…

From a Chatbot Arena battleThe same person sent this prompt to two anonymous models at once. Compare it with o3-2025-04-16’s answer.
  1. User

    give me an data set with 1000 rows simulating actual data with these variables Liquidity Ratios: Need Current Assets, Current Liabilities, Cash, Inventory, Accounts Receivable. Profitability Ratios: Net Income, Gross Profit, Operating Income, Revenue. Efficiency Ratios: Revenue, Assets, Inventory, Receivables, Payables, Employees. Leverage Ratios: Total Debt, Equity, Interest Expense. Valuation Multiples: Market Cap, Enterprise Value, EBITDA, EPS, Book Value Per Share. Growth Rates: YoY changes in Revenue, Net Income, EPS, Free Cash Flow.

  2. Claude Assistant

    I'll create a realistic financial dataset with 1000 rows representing quarterly data for 50 companies over 5 years (2019-2023). This dataset will include all the variables needed for the ratio analyses you mentioned.

    import pandas as pd
    import numpy as np
    from datetime import datetime, timedelta
    import random
    
    # Set random seed for reproducibility
    np.random.seed(42)
    random.seed(42)
    
    # Define companies and industries
    companies = [
        ("Apple Inc.", "AAPL", "Technology", "Large"),
        ("Microsoft Corp.", "MSFT", "Technology", "Large"),
        ("Amazon.com Inc.", "AMZN", "E-Commerce", "Large"),
        ("JPMorgan Chase", "JPM", "Banking", "Large"),
        ("Johnson & Johnson", "JNJ", "Healthcare", "Large"),
        ("Walmart Inc.", "WMT", "Retail", "Large"),
        ("Procter & Gamble", "PG", "Consumer Goods", "Large"),
        ("Tesla Inc.", "TSLA", "Automotive", "Large"),
        ("Coca-Cola Co.", "KO", "Beverages", "Large"),
        ("Netflix Inc.", "NFLX", "Entertainment", "Large"),
        ("Pfizer Inc.", "PFE", "Pharmaceuticals", "Large"),
        ("ExxonMobil Corp.", "XOM", "Energy", "Large"),
        ("Bank of America", "BAC", "Banking", "Large"),
        ("Home Depot Inc.", "HD", "Retail", "Large"),
        ("Visa Inc.", "V", "Financial Services", "Large"),
        ("UnitedHealth Group", "UNH", "Healthcare", "Large"),
        ("Mastercard Inc.", "MA", "Financial Services", "Large"),
        ("NVIDIA Corp.", "NVDA", "Technology", "Large"),
        ("Adobe Inc.", "ADBE", "Technology", "Mid"),
        ("Salesforce Inc.", "CRM", "Technology", "Mid"),
        ("PayPal Holdings", "PYPL", "Financial Services", "Mid"),
        ("Starbucks Corp.", "SBUX", "Restaurants", "Mid"),
        ("Target Corp.", "TGT", "Retail", "Mid"),
        ("CVS Health Corp.", "CVS", "Healthcare", "Mid"),
        ("General Motors", "GM", "Automotive", "Mid"),
        ("Ford Motor Co.", "F", "Automotive", "Mid"),
        ("Delta Air Lines", "DAL", "Airlines", "Mid"),
        ("American Airlines", "AAL", "Airlines", "Mid"),
        ("Marriott Intl.", "MAR", "Hotels", "Mid"),
        ("Hilton Worldwide", "HLT", "Hotels", "Mid"),
        ("Chipotle Mexican", "CMG", "Restaurants", "Mid"),
        ("McDonald's Corp.", "MCD", "Restaurants", "Mid"),
        ("Yum! Brands Inc.", "YUM", "Restaurants", "Mid"),
        ("Best Buy Co.", "BBY", "Retail", "Mid"),
        ("Gap Inc.", "GPS", "Retail", "Small"),
        ("Macy's Inc.", "M", "Retail", "Small"),
        ("Nordstrom Inc.", "JWN", "Retail", "Small"),
        ("Peloton Interactive", "PTON", "Fitness", "Small"),
        ("Zoom Video", "ZM", "Technology", "Small"),
        ("DocuSign Inc.", "DOCU", "Technology", "Small"),
        ("Spotify Technology", "SPOT", "Entertainment", "Small"),
        ("Square Inc.", "SQ", "Financial Services", "Small"),
        ("Robinhood Markets", "HOOD", "Financial Services", "Small"),
        ("DoorDash Inc.", "DASH", "Technology", "Small"),
        ("Airbnb Inc.", "ABNB", "Travel", "Small"),
        ("Uber Technologies", "UBER", "Technology", "Small"),
        ("Lyft Inc.", "LYFT", "Technology", "Small"),
        ("Pinterest Inc.", "PINS", "Technology", "Small"),
        ("Snap Inc.", "SNAP", "Technology", "Small"),
        ("Twitter Inc.", "TWTR", "Technology", "Small")
    ]
    
    # Industry characteristics (for realistic data generation)
    industry_profiles = {
        "Technology": {"margin": 0.25, "asset_turnover": 0.8, "debt_ratio": 0.3, "growth": 0.15},
        "Banking": {"margin": 0.30, "asset_turnover": 0.05, "debt_ratio": 0.85, "growth": 0.08},
        "Healthcare": {"margin": 0.20, "asset_turnover": 0.6, "debt_ratio": 0.4, "growth": 0.10},
        "Retail": {"margin": 0.05, "asset_turnover": 2.0, "debt_ratio": 0.5, "growth": 0.05},
        "E-Commerce": {"margin": 0.03, "asset_turnover": 1.5, "debt_ratio": 0.4, "growth": 0.20},
        "Consumer Goods": {"margin": 0.15, "asset_turnover": 0.8, "debt_ratio": 0.4, "growth": 0.04},
        "Automotive": {"margin": 0.08, "asset_turnover": 0.9, "debt_ratio": 0.6, "growth": 0.03},
        "Energy": {"margin": 0.10, "asset_turnover": 0.5, "debt_ratio": 0.5, "growth": 0.02},
        "Financial Services": {"margin": 0.35, "asset_turnover": 0.1, "debt_ratio": 0.3, "growth": 0.12},
        "Pharmaceuticals": {"margin": 0.22, "asset_turnover": 0.5, "debt_ratio": 0.4, "growth": 0.08},
        "Beverages": {"margin": 0.20, "asset_turnover": 0.6, "debt_ratio": 0.5, "growth": 0.06},
        "Entertainment": {"margin": 0.15, "asset_turnover": 0.7, "debt_ratio": 0.5, "growth": 0.15},
        "Restaurants": {"margin": 0.08, "asset_turnover": 1.5, "debt_ratio": 0.6, "growth": 0.07},
        "Airlines": {"margin": 0.05, "asset_turnover": 0.8, "debt_ratio": 0.7, "growth": 0.04},
        "Hotels": {"margin": 0.12, "asset_turnover": 0.4, "debt_ratio": 0.6, "growth": 0.06},
        "Fitness": {"margin": 0.10, "asset_turnover": 0.6, "debt_ratio": 0.5, "growth": 0.20},
        "Travel": {"margin": 0.15, "asset_turnover": 0.8, "debt_ratio": 0.4, "growth": 0.25}
    }
    
    # Generate data
    data = []
    
    for company_name, ticker, industry, size in companies:
        # Get industry profile
        profile = industry_profiles.get(industry, industry_profiles["Technology"])
        
        # Base values (in millions) - vary by company size
        if size == "Large":
            base_revenue = np.random.uniform(20000, 100000)
            base_assets = base_revenue / profile["asset_turnover"] * np.random.uniform(0.8, 1.2)
            base_employees = int(np.random.uniform(50000, 200000))
        elif size == "Mid":
            base_revenue = np.random.uniform(5000, 20000)
            base_assets = base_revenue / profile["asset_turnover"] * np.random.uniform(0.8, 1.2)
            base_employees = int(np.random.uniform(10000, 50000))
        else:  # Small
            base_revenue = np.random.uniform(500, 5000)
            base_assets = base_revenue / profile["asset_turnover"] * np.random.uniform(0.8, 1.2)
            base_employees = int(np.random.uniform(1000, 10000))
        
        # Generate quarterly data for 5 years (2019-2023)
        for year in range(2019, 2024):
            for quarter in range(1, 5):
                # Date
                date = f"{year}-Q{quarter}"
                
                # Apply growth and seasonality
                years_from_start = year - 2019 + (quarter - 1) / 4
                growth_factor = (1 + profile["growth"]) ** years_from_start
                seasonal_factor = 1 + 0.1 * np.sin(2 * np.pi * (quarter - 1) / 4)  # Seasonal variation
                
                # Revenue (with some randomness)
                revenue = base_revenue * growth_factor * seasonal_factor * np.random.uniform(0.9, 1.1)
                
                # Profitability metrics
                gross_margin = profile["margin"] * np.random.uniform(0.8, 1.2)
                gross_profit = revenue * gross_margin
                
                operating_margin = gross_margin * np.random.uniform(0.6, 0.9)
                operating_income = revenue * operating_margin
                
                net_margin = operating_margin * np.random.uniform(0.6, 0.85)
                net_income = revenue * net_margin
                
                # Balance Sheet Items
                total_assets = base_assets * growth_factor * np.random.uniform(0.95, 1.05)
                
                # Current assets components
                current_ratio = np.random.uniform(1.0, 2.5)
                current_assets_ratio = np.random.uniform(0.3, 0.5)
                current_assets = total_assets * current_assets_ratio
                
                cash_ratio = np.random.uniform(0.2, 0.4)
                cash = current_assets * cash_ratio
                
                receivables_days = np.random.uniform(30, 90)
                accounts_receivable = (revenue / 4) * (receivables_days / 90)
                
                inventory_turnover = np.random.uniform(4, 12)
                if industry in ["Banking", "Financial Services", "Technology"]:
                    inventory = 0  # Service companies have no inventory
                else:
                    inventory = (revenue * (1 - gross_margin) / 4) / (inventory_turnover / 4)
                
                # Current liabilities
                current_liabilities = current_assets / current_ratio
                
                payables_days = np.random.uniform(30, 60)
                accounts_payable = (revenue * (1 - gross_margin) / 4) * (payables_days / 90)
                
                # Debt and Equity
                debt_to_assets = profile["debt_ratio"] * np.random.uniform(0.7, 1.3)
                total_debt = total_assets * debt_to_assets
                equity = total_assets - total_debt - current_liabilities
                
                # Interest expense (assuming 4-6% interest rate)
                interest_rate = np.random.uniform(0.04, 0.06)
                interest_expense = total_debt * interest_rate / 4  # Quarterly
                
                # Market data
                pe_ratio = np.random.uniform(10, 35)
                shares_outstanding = np.random.uniform(100, 5000)  # In millions
                eps = net_income / shares_outstanding
                stock_price = eps * pe_ratio * 4  # Annualized EPS
                market_cap = stock_price * shares_outstanding
                
                # Enterprise Value
                enterprise_value = market_cap + total_debt - cash
                
                # EBITDA (approximation)
                depreciation_rate = 0.05  # 5% of assets per year
                depreciation = total_assets * depreciation_rate / 4
                ebitda = operating_income + depreciation
                
                # Book value per share
                book_value_per_share = equity / shares_outstanding
                
                # Employees (with some growth)
                employees = int(base_employees * growth_factor * np.random.uniform(0.95, 1.05))
                
                # Free Cash Flow (simplified)
                capex = total_assets * 0.03  # 3% of assets
                working_capital_change = (accounts_receivable + inventory - accounts_payable) * 0.1
                free_cash_flow = net_income + depreciation - capex - working_capital_change
                
                # Create row
                row = {
                    "Company_Name": company_name,
                    "Ticker": ticker,
                    "Industry": industry,
                    "Date": date,
                    "Year": year,
                    "Quarter": quarter,
                    
                    # Income Statement
                    "Revenue": round(revenue, 2),
                    "Gross_Profit": round(gross_profit, 2),
                    "Operating_Income": round(operating_income, 2),
                    "Net_Income": round(net_income, 2),
                    "Interest_Expense": round(interest_expense, 2),
                    
                    # Balance Sheet
                    "Total_Assets": round(total_assets, 2),
                    "Current_Assets": round(current_assets, 2),
                    "Cash": round(cash, 2),
                    "Accounts_Receivable": round(accounts_receivable, 2),
                    "Inventory": round(inventory, 2),
                    "Current_Liabilities": round(current_liabilities, 2),
                    "Accounts_Payable": round(accounts_payable, 2),
                    "Total_Debt": round(total_debt, 2),
                    "Equity": round(equity, 2),
                    
                    # Market Data
                    "Market_Cap": round(market_cap, 2),
                    "Enterprise_Value": round(enterprise_value, 2),
                    "Stock_Price": round(stock_price, 2),
                    "Shares_Outstanding": round(shares_outstanding, 2),
                    "EPS": round(eps, 4),
                    "Book_Value_Per_Share": round(book_value_per_share, 2),
                    
                    # Other Metrics
                    "EBITDA": round(ebitda, 2),
                    "Free_Cash_Flow": round(free_cash_flow, 2),
                    "Employees": employees
                }
                
                data.append(row)
    
    # Create DataFrame
    df = pd.DataFrame(data)
    
    # Calculate YoY growth rates
    df = df.sort_values(['Ticker', 'Year', 'Quarter'])
    
    for ticker in df['Ticker'].unique():
        mask = df['Ticker'] == ticker
        ticker_data = df[mask].copy()
        
        # Calculate YoY changes
        df.loc[mask, 'Revenue_YoY_Growth'] = ticker_data['Revenue'].pct_change(4)
        df.loc[mask, 'Net_Income_YoY_Growth'] = ticker_data['Net_Income'].pct_change(4)
        df.loc[mask, 'EPS_YoY_Growth'] = ticker_data['EPS'].pct_change(4)
        df.loc[mask, 'FCF_YoY_Growth'] = ticker_data['Free_Cash_Flow'].pct_change(4)
    
    # Fill NaN values in growth rates with 0
    growth_columns = ['Revenue_YoY_Growth', 'Net_Income_YoY_Growth', 'EPS_YoY_Growth', 'FCF_YoY_Growth']
    df[growth_columns] = df[growth_columns].fillna(0)
    
    # Round growth rates
    for col in growth_columns:
        df[col] = df[col].round(4)
    
    # Display first few rows
    print(f"Dataset shape: {df.shape}")
    print("\nFirst 5 rows:")
    print(df.head())
    
    # Save to CSV
    df.to_csv('financial_analysis_dataset.csv', index=False)
    print("\nDataset saved to 'financial_analysis_dataset.csv'")
    
    # Display summary statistics
    print("\nSummary by Industry:")
    

Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.