Overall Statistics
Total Trades
431
Average Win
1.97%
Average Loss
-2.37%
Compounding Annual Return
1.284%
Drawdown
30.300%
Expectancy
0.078
Net Profit
30.284%
Sharpe Ratio
0.157
Probabilistic Sharpe Ratio
0.001%
Loss Rate
41%
Win Rate
59%
Profit-Loss Ratio
0.83
Alpha
0.016
Beta
-0.014
Annual Standard Deviation
0.099
Annual Variance
0.01
Information Ratio
-0.24
Tracking Error
0.206
Treynor Ratio
-1.101
Total Fees
$15498.46
class EarningsQualityFactor(QCAlgorithm):

    def Initialize(self):
        self.SetStartDate(2000,1,1)   #Set Start Date
        self.SetCash(1000000)         #Set Strategy Cash
        
        self.UniverseSettings.Resolution = Resolution.Daily
        self.previous_fine = None
        self.long = None
        self.short = None
        self.AddUniverse(self.CoarseSelectionFunction,self.FineSelectionFunction)
        self.AddEquity("SPY", Resolution.Daily)
        # monthly scheduled event but will only rebalance once a year
        self.Schedule.On(self.DateRules.MonthStart("SPY"), self.TimeRules.At(23, 0), self.rebalance)
        self.yearly_rebalance = False
        
    def CoarseSelectionFunction(self, coarse):
        if self.yearly_rebalance:
            # drop stocks which have no fundamental data
            filtered_coarse = [x.Symbol for x in coarse if (x.HasFundamentalData) and (x.Market == "usa")]
            return filtered_coarse
        else: 
            return []      
    
    def FineSelectionFunction(self, fine):
        if self.yearly_rebalance:
            #filters out the non-financial companies that don't contain the necessary data
            fine = [x for x in fine if (x.CompanyReference.IndustryTemplateCode != "B")
                                    and (x.FinancialStatements.BalanceSheet.CurrentAssets.Value != 0) 
                                    and (x.FinancialStatements.BalanceSheet.CashAndCashEquivalents.Value != 0)
                                    and (x.FinancialStatements.BalanceSheet.CurrentLiabilities.Value != 0)
                                    and (x.FinancialStatements.BalanceSheet.CurrentDebt.Value != 0)
                                    and (x.FinancialStatements.BalanceSheet.IncomeTaxPayable.Value != 0)
                                    and (x.FinancialStatements.IncomeStatement.DepreciationAndAmortization.Value != 0)]
            
            if not self.previous_fine:
                # will wait one year in order to have the historical fundamental data
                self.previous_fine = fine
                self.yearly_rebalance = False
                return []
            else:
                # calculate the accrual for each stock
                fine = self.CalculateAccruals(fine, self.previous_fine)
                filtered_fine = [x for x in fine if (x.FinancialStatements.CashFlowStatement.OperatingCashFlow.Value!=0) 
                                                and (x.EarningReports.BasicEPS.Value!=0)
                                                and (x.EarningReports.BasicAverageShares.Value!=0)
                                                and (x.OperationRatios.DebttoAssets.Value!=0)
                                                and (x.OperationRatios.ROE.Value!=0)]
                for i in filtered_fine:
                    # cash flow to assets
                    i.CFA = i.FinancialStatements.CashFlowStatement.OperatingCashFlow.Value/(i.EarningReports.BasicEPS.Value * i.EarningReports.BasicAverageShares.Value)
                    # debt to assets
                    i.DA = i.OperationRatios.DebttoAssets.Value
                    # return on equity
                    i.ROE = i.OperationRatios.ROE.Value

                # sort stocks by four factors respectively
                sortedByAccrual = sorted(filtered_fine, key=lambda x: x.Accrual, reverse=True) # high score with low accrual 
                sortedByCFA = sorted(filtered_fine, key=lambda x: x.CFA)                       # high score with high CFA
                sortedByDA = sorted(filtered_fine, key=lambda x: x.DA, reverse=True)           # high score with low leverage
                sortedByROE = sorted(filtered_fine, key=lambda x: x.ROE)                       # high score with high ROE
                # create dict to save the score for each stock           
                score_dict = {}
                # assign a score to each stock according to their rank with different factors
                for i,obj in enumerate(sortedByAccrual):
                    scoreAccrual = i
                    scoreCFA = sortedByCFA.index(obj)
                    scoreDA = sortedByDA.index(obj)
                    scoreROE = sortedByROE.index(obj)
                    score = scoreAccrual + scoreCFA + scoreDA + scoreROE
                    score_dict[obj.Symbol] = score
                    
                sortedByScore = sorted(score_dict, key = lambda x: score_dict[x], reverse = True)
                # long stocks with the top score (>30%) and short stocks with the bottom score (<70%)                 
                self.long = sortedByScore[:int(0.3*len(sortedByScore))]
                self.short = sortedByScore[-int(0.3*len(sortedByScore)):]

                # save the fine data for the next year's analysis
                self.previous_fine = fine
                
                return self.long + self.short
        else:
            return []
    
    def CalculateAccruals(self, current, previous):
        accruals = []
        for stock_data in current:
            #compares this and last year's fine fundamental objects
            try:
                prev_data = None
                for x in previous:
                    if x.Symbol == stock_data.Symbol:
                        prev_data = x
                        break
                
                #calculates the balance sheet accruals and adds the property to the fine fundamental object
                delta_assets = float(stock_data.FinancialStatements.BalanceSheet.CurrentAssets.Value)-float(prev_data.FinancialStatements.BalanceSheet.CurrentAssets.Value)
                delta_cash = float(stock_data.FinancialStatements.BalanceSheet.CashAndCashEquivalents.Value)-float(prev_data.FinancialStatements.BalanceSheet.CashAndCashEquivalents.Value)
                delta_liabilities = float(stock_data.FinancialStatements.BalanceSheet.CurrentLiabilities.Value)-float(prev_data.FinancialStatements.BalanceSheet.CurrentLiabilities.Value)
                delta_debt = float(stock_data.FinancialStatements.BalanceSheet.CurrentDebt.Value)-float(prev_data.FinancialStatements.BalanceSheet.CurrentDebt.Value)
                delta_tax = float(stock_data.FinancialStatements.BalanceSheet.IncomeTaxPayable.Value)-float(prev_data.FinancialStatements.BalanceSheet.IncomeTaxPayable.Value)
                dep = float(stock_data.FinancialStatements.IncomeStatement.DepreciationAndAmortization.Value)
                avg_total = (float(stock_data.FinancialStatements.BalanceSheet.TotalAssets.Value)+float(prev_data.FinancialStatements.BalanceSheet.TotalAssets.Value))/2
                #accounts for the size difference
                stock_data.Accrual = ((delta_assets-delta_cash)-(delta_liabilities-delta_debt-delta_tax)-dep)/avg_total
                accruals.append(stock_data)
            except:
                #value in current universe does not exist in the previous universe
                pass
        return accruals
    
    def rebalance(self):
        #yearly rebalance at the end of June (start of July)
        if self.Time.month == 7:
            self.yearly_rebalance = True

    def OnData(self, data):
        if not self.yearly_rebalance: return 
        if self.long and self.short:
            long_stocks = [x.Key for x in self.Portfolio if x.Value.IsLong]
            short_stocks = [x.Key for x in self.Portfolio if x.Value.IsShort]
            # liquidate the stocks not in the filtered long/short list
            for long in long_stocks:
                if long not in self.long:
                    self.Liquidate(long)
                    
            for short in short_stocks:
                if short not in self.short:
                    self.Liquidate(short)
        
            long_weight = 0.8/len(self.long)
            for i in self.long:
                self.SetHoldings(i, long_weight)
            short_weight = 0.8/len(self.short)
            for i in self.short:
                self.SetHoldings(i, -short_weight)            


            self.yearly_rebalance = False
            self.long = False
            self.short = False
import numpy as np
from scipy.optimize import minimize
import statsmodels.api as sm

sp100_stocks = ['AAPL','MSFT','AMZN','FB','BRKB','GOOGL','GOOG','JPM','JNJ','V','PG','XOM','UNH','BAC','MA','T','DIS','INTC','HD','VZ','MRK','PFE','CVX','KO','CMCSA','CSCO','PEP','WFC','C','BA','ADBE','WMT','CRM','MCD','MDT','BMY','ABT','NVDA','NFLX','AMGN','PM','PYPL','TMO','COST','ABBV','ACN','HON','NKE','UNP','UTX','NEE','IBM','TXN','AVGO','LLY','ORCL','LIN','SBUX','AMT','LMT','GE','MMM','DHR','QCOM','CVS','MO','LOW','FIS','AXP','BKNG','UPS','GILD','CHTR','CAT','MDLZ','GS','USB','CI','ANTM','BDX','TJX','ADP','TFC','CME','SPGI','COP','INTU','ISRG','CB','SO','D','FISV','PNC','DUK','SYK','ZTS','MS','RTN','AGN','BLK']

def MonthDiff(d1, d2):
    return (d1.year - d2.year) * 12 + d1.month - d2.month

def Return(values):
    return (values[-1] - values[0]) / values[0]
    
def Volatility(values):
    values = np.array(values)
    returns = (values[1:] - values[:-1]) / values[:-1]
    return np.std(returns)  

def MultipleLinearRegression(x, y):
    x = np.array(x).T
    x = sm.add_constant(x)
    result = sm.OLS(endog=y, exog=x).fit()
    return result
    
# Custom fee model
class CustomFeeModel(FeeModel):
    def GetOrderFee(self, parameters):
        fee = parameters.Security.Price * parameters.Order.AbsoluteQuantity * 0.00005
        return OrderFee(CashAmount(fee, "USD"))

# Quandl free data
class QuandlFutures(PythonQuandl):
    def __init__(self):
        self.ValueColumnName = "settle"

# Quandl "value" data
class QuandlValue(PythonQuandl):
    def __init__(self):
        self.ValueColumnName = 'Value'

# Quandl short interest data.
class QuandlFINRA_ShortVolume(PythonQuandl):
    def __init__(self):
        self.ValueColumnName = 'SHORTVOLUME'    # also 'TOTALVOLUME' is accesible

# Commitments of Traders data.
# NOTE: IMPORTANT: Data order must be ascending (datewise).
# Data source: https://commitmentsoftraders.org/cot-data/
# Data description: https://commitmentsoftraders.org/wp-content/uploads/Static/CoTData/file_key.html
class CommitmentsOfTraders(PythonData):
    def GetSource(self, config, date, isLiveMode):
        return SubscriptionDataSource("data.quantpedia.com/backtesting_data/futures/cot/{0}.PRN".format(config.Symbol.Value), SubscriptionTransportMedium.RemoteFile, FileFormat.Csv)

    # File example.
    # DATE   OPEN     HIGH        LOW       CLOSE     VOLUME   OI
    # ----   ----     ----        ---       -----     ------   --
    # DATE   LARGE    SPECULATOR  COMMERCIAL HEDGER   SMALL TRADER
    #        LONG     SHORT       LONG      SHORT     LONG     SHORT
    def Reader(self, config, line, date, isLiveMode):
        data = CommitmentsOfTraders()
        data.Symbol = config.Symbol
        
        if not line[0].isdigit(): return None
        split = line.split(',')
        
        # Prevent lookahead bias.
        data.Time = datetime.strptime(split[0], "%Y%m%d") + timedelta(days=1)
        
        data['LARGE_SPECULATOR_LONG'] = int(split[1])
        data['LARGE_SPECULATOR_SHORT'] = int(split[2])
        data['COMMERCIAL_HEDGER_LONG'] = int(split[3])
        data['COMMERCIAL_HEDGER_SHORT'] = int(split[4])
        data['SMALL_TRADER_LONG'] = int(split[5])
        data['SMALL_TRADER_SHORT'] = int(split[6])
        data['open_interest'] = int(split[1]) + int(split[2]) + int(split[3]) + int(split[4]) + int(split[5]) + int(split[6])
        data.Value = int(split[1])

        return data

# Quantpedia bond yield data.
# NOTE: IMPORTANT: Data order must be ascending (datewise)
class QuantpediaIndices(PythonData):
    def GetSource(self, config, date, isLiveMode):
        return SubscriptionDataSource("data.quantpedia.com/backtesting_data/index/{0}.csv".format(config.Symbol.Value), SubscriptionTransportMedium.RemoteFile, FileFormat.Csv)

    def Reader(self, config, line, date, isLiveMode):
        data = QuantpediaIndices()
        data.Symbol = config.Symbol
        
        if not line[0].isdigit(): return None
        split = line.split(',')
        
        data.Time = datetime.strptime(split[0], "%Y-%m-%d") + timedelta(days=1)
        data['close'] = float(split[1])
        data.Value = float(split[1])

        return data

# Quantpedia bond yield data.
# NOTE: IMPORTANT: Data order must be ascending (datewise)
class QuantpediaBondYield(PythonData):
    def GetSource(self, config, date, isLiveMode):
        return SubscriptionDataSource("data.quantpedia.com/backtesting_data/bond_yield/{0}.csv".format(config.Symbol.Value), SubscriptionTransportMedium.RemoteFile, FileFormat.Csv)

    def Reader(self, config, line, date, isLiveMode):
        data = QuantpediaBondYield()
        data.Symbol = config.Symbol
        
        if not line[0].isdigit(): return None
        split = line.split(',')
        
        data.Time = datetime.strptime(split[0], "%Y-%m-%d") + timedelta(days=1)
        data['yield'] = float(split[1])
        data.Value = float(split[1])

        return data

# Quantpedia data.
# NOTE: IMPORTANT: Data order must be ascending (datewise)
class QuantpediaFutures(PythonData):
    def GetSource(self, config, date, isLiveMode):
        return SubscriptionDataSource("data.quantpedia.com/backtesting_data/futures/{0}.csv".format(config.Symbol.Value), SubscriptionTransportMedium.RemoteFile, FileFormat.Csv)

    def Reader(self, config, line, date, isLiveMode):
        data = QuantpediaFutures()
        data.Symbol = config.Symbol
        
        if not line[0].isdigit(): return None
        split = line.split(';')
        
        data.Time = datetime.strptime(split[0], "%d.%m.%Y") + timedelta(days=1)
        data['back_adjusted'] = float(split[1])
        data['spliced'] = float(split[2])
        data.Value = float(split[1])

        return data

# Commitments of Traders data.
# NOTE: IMPORTANT: Data order must be ascending (datewise).
# Data source: https://commitmentsoftraders.org/cot-data/
# Data description: https://commitmentsoftraders.org/wp-content/uploads/Static/CoTData/file_key.html
class CommitmentsOfTraders(PythonData):
    def GetSource(self, config, date, isLiveMode):
        return SubscriptionDataSource("data.quantpedia.com/backtesting_data/futures/cot/{0}.PRN".format(config.Symbol.Value), SubscriptionTransportMedium.RemoteFile, FileFormat.Csv)

    # File example.
    # DATE   OPEN     HIGH        LOW       CLOSE     VOLUME   OI
    # ----   ----     ----        ---       -----     ------   --
    # DATE   LARGE    SPECULATOR  COMMERCIAL HEDGER   SMALL TRADER
    #        LONG     SHORT       LONG      SHORT     LONG     SHORT
    def Reader(self, config, line, date, isLiveMode):
        data = CommitmentsOfTraders()
        data.Symbol = config.Symbol
        
        if not line[0].isdigit(): return None
        split = line.split(',')
        
        # Prevent lookahead bias.
        data.Time = datetime.strptime(split[0], "%Y%m%d") + timedelta(days=1)
        
        data['LARGE_SPECULATOR_LONG'] = int(split[1])
        data['LARGE_SPECULATOR_SHORT'] = int(split[2])
        data['COMMERCIAL_HEDGER_LONG'] = int(split[3])
        data['COMMERCIAL_HEDGER_SHORT'] = int(split[4])
        data['SMALL_TRADER_LONG'] = int(split[5])
        data['SMALL_TRADER_SHORT'] = int(split[6])

        data.Value = int(split[1])

        return data
        
# NOTE: Manager for new trades. It's represented by certain count of equally weighted brackets for long and short positions.
# If there's a place for new trade, it will be managed for time of holding period.
class TradeManager():
    def __init__(self, algorithm, long_size, short_size, holding_period):
        self.algorithm = algorithm  # algorithm to execute orders in.
        
        self.long_size = long_size
        self.short_size = short_size
        
        self.long_len = 0
        self.short_len = 0
    
        # Arrays of ManagedSymbols
        self.symbols = []
        
        self.holding_period = holding_period    # Days of holding.
    
    # Add stock symbol object
    def Add(self, symbol, long_flag):
        # Open new long trade.
        managed_symbol = ManagedSymbol(symbol, self.holding_period, long_flag)
        
        if long_flag:
            # If there's a place for it.
            if self.long_len < self.long_size:
                self.symbols.append(managed_symbol)
                self.algorithm.SetHoldings(symbol, 1 / self.long_size)
                self.long_len += 1
            else:
                self.algorithm.Log("There's not place for additional trade.")

        # Open new short trade.
        else:
            # If there's a place for it.
            if self.short_len < self.short_size:
                self.symbols.append(managed_symbol)
                self.algorithm.SetHoldings(symbol, - 1 / self.short_size)
                self.short_len += 1
            else:
                self.algorithm.Log("There's not place for additional trade.")
   
    # Decrement holding period and liquidate symbols.
    def TryLiquidate(self):
        symbols_to_delete = []
        for managed_symbol in self.symbols:
            managed_symbol.days_to_liquidate -= 1
            
            # Liquidate.
            if managed_symbol.days_to_liquidate == 0:
                symbols_to_delete.append(managed_symbol)
                self.algorithm.Liquidate(managed_symbol.symbol)
                
                if managed_symbol.long_flag: self.long_len -= 1
                else: self.short_len -= 1

        # Remove symbols from management.
        for managed_symbol in symbols_to_delete:
            self.symbols.remove(managed_symbol)
    
    def LiquidateTicker(self, ticker):
        symbol_to_delete = None
        for managed_symbol in self.symbols:
            if managed_symbol.symbol.Value == ticker:
                self.algorithm.Liquidate(managed_symbol.symbol)
                symbol_to_delete = managed_symbol
                if managed_symbol.long_flag: self.long_len -= 1
                else: self.short_len -= 1
                
                break
        
        if symbol_to_delete: self.symbols.remove(symbol_to_delete)
        else: self.algorithm.Debug("Ticker is not held in portfolio!")
    
class ManagedSymbol():
    def __init__(self, symbol, days_to_liquidate, long_flag):
        self.symbol = symbol
        self.days_to_liquidate = days_to_liquidate
        self.long_flag = long_flag
        
class PortfolioOptimization(object):
    def __init__(self, df_return, risk_free_rate, num_assets):
        self.daily_return = df_return
        self.risk_free_rate = risk_free_rate
        self.n = num_assets # numbers of risk assets in portfolio
        self.target_vol = 0.05

    def annual_port_return(self, weights):
        # calculate the annual return of portfolio
        return np.sum(self.daily_return.mean() * weights) * 252

    def annual_port_vol(self, weights):
        # calculate the annual volatility of portfolio
        return np.sqrt(np.dot(weights.T, np.dot(self.daily_return.cov() * 252, weights)))

    def min_func(self, weights):
        # method 1: maximize sharp ratio
        return - self.annual_port_return(weights) / self.annual_port_vol(weights)
        
        # method 2: maximize the return with target volatility
        #return - self.annual_port_return(weights) / self.target_vol

    def opt_portfolio(self):
        # maximize the sharpe ratio to find the optimal weights
        cons = ({'type': 'eq', 'fun': lambda x: np.sum(x) - 1})
        bnds = tuple((0, 1) for x in range(2)) + tuple((0, 0.25) for x in range(self.n - 2))
        opt = minimize(self.min_func,                               # object function
                       np.array(self.n * [1. / self.n]),            # initial value
                       method='SLSQP',                              # optimization method
                       bounds=bnds,                                 # bounds for variables 
                       constraints=cons)                            # constraint conditions
                      
        opt_weights = opt['x']
 
        return opt_weights