Details about Portfolio construction and risk managemnet

In live trading, the SetCash method is ignored and your brokerage cash is used instead. This means that if you have $10,000 in your brokerage account, that is the amount that will be used for your algorithm. However, if you want to limit the amount of cash used by your algorithm to $1,000, you can do this programmatically by adjusting the order size in your algorithm.

For example, if you want to buy a certain stock, instead of using SetHoldings("SYMBOL", .33), which would use 33% of your total cash, you can use MarketOrder("SYMBOL", (int) (1000 / price)), which would only use $1,000 of your cash.

This is not done in Portfolio Construction or Risk Management, but directly in your algorithm. Your Alpha Model, which returns direction with weight, would not be affected by this.

Here is the relevant discussion from the QuantConnect forum: SetCash Method

Please note that if you want to add more cash to your live algorithm, you need to stop the algorithm, add the funds, then redeploy. There is no need to clone. Here is the relevant discussion from the QuantConnect forum: How can I add cash to my portfolio when strategy is running?

Thanks Mia Alissi 

But I'm not using SetHoldings("SYMBOL", .33)  or any things like this

My stretagy flow is Alpha Model → Portfolio Construction → Execute Model

I do not do anything manually to place order So I think I have to change in Portfolio Construction like How much Quantity should I place. 

In your case, you can control the quantity of orders in the Portfolio Construction Model (PCM). The PCM is responsible for determining the target quantities for each security based on the insights provided by the Alpha Model.

You can create a custom PCM that keeps track of the quantity of each security that each alpha model has opened. Here's a Python example of how you could implement this:

class CustomPCM(PortfolioConstructionModel):
    def __init__(self):
        self.alpha_positions = {}

    def CreateTargets(self, algorithm, insights):
        targets = []

        for insight in insights:
            # Get the current quantity of the security for the alpha model
            current_quantity = self.alpha_positions.get(insight.SourceModel, {}).get(insight.Symbol, 0)

            # Check if the alpha model has reached the maximum quantity for the security
            if abs(current_quantity + insight.Magnitude) > 15:
                continue

            # Update the quantity of the security for the alpha model
            self.alpha_positions.setdefault(insight.SourceModel, {})[insight.Symbol] = current_quantity + insight.Magnitude

            # Create a target for the insight
            targets.append(PortfolioTarget(insight.Symbol, insight.Magnitude))

        return targets

In this example, the PCM keeps track of the quantity of each security that each alpha model has opened. It then uses this information to create targets for each insight. If the alpha model has reached the maximum quantity for a security, it skips that insight. Otherwise, it updates the quantity of the security for the alpha model and creates a target for the insight.

This is just an example and you might need to adjust it according to your specific needs. For example, you might want to limit the total quantity of all securities to a certain amount, or you might want to adjust the maximum quantity for each security based on other factors.

Here is the relevant discussion from the QuantConnect forum: Managing multiple independent Alpha Models