Turn of the Month Effect in the Cross-Section of Stock Returns

1from AlgorithmImports import *
2from pandas.tseries.offsets import BDay
3from pandas.tseries.offsets import BMonthEnd
4from typing import List, Dict, Tuple
5#endregion
6class TOTMCrossSection(QCAlgorithm):
7def Initialize(self):
8self.SetStartDate(2000, 1, 1)
9self.SetCash(100000)
10self.leverage:int = 5
11self.quantile:int = 10
12self.min_share_price:int = 5
13self.offset_days:int = 4
14self.fundamental_sorting_key = lambda x: x.DollarVolume
15self.fundamental_count:int = 1000
16self.selection_flag:bool = False 
17self.traded_this_month:bool = True
18
19self.data:Dict[Symbol, SymbolData] = {}
20self.long:List[Symbol] = []
21self.short:List[Symbol] = []
22self.period:int = 5 # T-8 to T-4
23
24self.symbol:Symbol = self.AddEquity('SPY', Resolution.Daily).Symbol
25self.close_days:int = 0
26self.close_flag:bool = False
27
28self.settings.daily_precise_end_time = False
29self.Settings.MinimumOrderMarginPortfolioPercentage = 0.
30self.UniverseSettings.Resolution = Resolution.Daily
31self.AddUniverse(self.FundamentalSelectionFunction)
32
33def OnSecuritiesChanged(self, changes: SecurityChanges) -> None:
34for security in changes.AddedSecurities:
35    security.SetFeeModel(CustomFeeModel())
36    security.SetLeverage(self.leverage)
37    
38def FundamentalSelectionFunction(self, fundamental: List[Fundamental]) -> List[Symbol]:
39# Update the rolling window every day.
40for stock in fundamental:
41    symbol:Symbol = stock.Symbol
42    # Store monthly price.
43    if symbol in self.data:
44        self.data[symbol].update(stock.AdjustedPrice)
45if not self.selection_flag:
46    return Universe.Unchanged
47self.selection_flag = False
48self.close_days = 0
49selected:List[Fundamental] = [
50    x for x in fundamental if x.HasFundamentalData and x.Price > self.min_share_price
51]
52
53if len(selected) > self.fundamental_count:
54    selected = [x for x in sorted(selected, key=self.fundamental_sorting_key, reverse=True)[:self.fundamental_count]]
55performances:Dict[Symbol, float] = {}     
56# Warmup price rolling windows.
57for stock in selected:
58    symbol:Symbol = stock.Symbol
59    if symbol not in self.data:
60        self.data[symbol] = SymbolData(self.period)
61        history:DataFrame = self.History(symbol, self.period, Resolution.Daily)
62        if history.empty:
63            self.Log(f"Not enough data for {symbol} yet")
64            continue
65        closes:Series = history.loc[symbol].close
66        for time, close in closes.items():
67            self.data[symbol].update(close)
68    if self.data[symbol].is_ready():
69        performances[symbol] = self.data[symbol].performance() # T-8 to T-4
70# Sort stocks based on performance        
71sorted_by_performance:List[Tuple[Symbol, float]] = sorted(performances.items(), key=lambda item: item[1], reverse=True)
72quantile:int = int(len(sorted_by_performance) / self.quantile)
73
74self.short = [x[0] for x in sorted_by_performance[:quantile]] # Best performance quantile
75self.long = [x[0] for x in sorted_by_performance[-quantile:]]
76return self.long + self.short
77def OnData(self, data: Slice) -> None:
78offset = BMonthEnd()
79last_day:datetime = offset.rollforward(self.Time)
80trigger_day:datetime = last_day - BDay(self.offset_days)
81if self.Time == trigger_day:
82    self.selection_flag = True
83    
84if self.Portfolio.Invested:
85    self.close_days += 1
86    if self.close_days == 6:
87        self.close_days = 0
88        self.Liquidate()
89    
90# Trade execution.
91targets:List[PortfolioTarget] = []
92for i, portfolio in enumerate([self.long, self.short]):
93    for symbol in portfolio:
94        if symbol in data and data[symbol]:
95            targets.append(PortfolioTarget(symbol, ((-1) ** i) / len(portfolio)))
96
97self.SetHoldings(targets, True)
98self.long.clear()
99self.short.clear()
100class SymbolData():
101def __init__(self, period:int):
102self._closes:RollingWindow = RollingWindow[float](period)
103
104def update(self, close: float) -> None:
105self._closes.Add(close)
106
107def is_ready(self) -> bool:
108return self._closes.IsReady
109
110def performance(self) -> float:
111return (self._closes[0] / self._closes[self._closes.Count - 1]) - 1
112# Custom fee model
113class CustomFeeModel(FeeModel):
114def GetOrderFee(self, parameters):
115fee = parameters.Security.Price * parameters.Order.AbsoluteQuantity * 0.00005
116return OrderFee(CashAmount(fee, "USD"))