Mosaic’s Post

If you're going to do an MMM, you should think a lot about how you are going to validate the model. How are you going to build trust in it? How are you going to know that it's right? The reality is that, with a flexible modeling methodology, there are often millions of ways that the model can go wrong and only one way that it can go right. There are a few different ways we think about validating MMMs at Recast:

Excellent video and summary on how to validate your MMM - don't rely on any statistical data fit metrics to assess how good your model is if you want to optimize campaign spend. There are only two ways to do this: 1) Compare the MMM lift to the lift of an experiment (which we trust more) 2) Make a SINGLE change based on the MMM recommendation and see whether the expected incremental sales change really materializes. This is different from being able to just predict tomorrow's number right = out-of-sample prediction. That's great for inventory planning but often very misleading for causal inferences.

If you're going to do an MMM, you should think a lot about how you are going to validate the model. How are you going to build trust in it? How are you going to know that it's right? The reality is that, with a flexible modeling methodology, there are often millions of ways that the model can go wrong and only one way that it can go right. There are a few different ways we think about validating MMMs at Recast:

Comment if you want it in your DM. I've been working on a pretty cool and simple cap table model in the train yesterday and will publish it soon with a short voice over. It takes into account SAFE, Equity, Secondary... I've seen a lot of great models, quite sophisticated, maybe too complex sometimes, while very often what we need is something simple to understand and very easy to edit :) Comment below if you want it in your DM, but also let me know what you've been struggling with when it comes to cap table modeling, I'd like to see whether I can improve this very first version with your immediate request for help... A couple of things that I will explain in more details... It's easier to have the totals on top and not at the bottom ! It's better not to have duplicated lists of shareholders...

3 - 5 year averages now available on the DCF builder.

News alert: valuation matters today! Our DCF models are an incredibly powerful valuation tool as many of you who’ve seen our Reverse DCF Case studies know (see them here: https://lnkd.in/gPGKtJNq). And, I have some news about those models. In case you’ve not seen, the team is hard at work making a lot of cool updates to our website and research tools. One of my favorite is the new charting tools for the Decision Page in our reverse DCF models. Words alone can’t do this update justice; so I put together a short video for everyone to see. Hey, I’m not a video producer, and I’m not getting an Academy awards for this video, but I think it gets the job done. In this short video, I am going to show everyone exactly why Tesla's stock ($TSLA) valuation is ridiculous. I welcome anyone to take the other side of that argument after watching this video. https://lnkd.in/gvAe_cQm

Say goodbye to the hassle of digging through endless PDFs to decipher your cap table history 👋 Introducing one of Mantle's most loved features: Timeline View 🕰️ Timeline View: Experience a visual journey through your company's cap table evolution, from genesis to the present day. 🔍 Filters & Search: Dive deep into your cap table by filtering by stakeholders or security types, gaining insights into ownership shifts and past financing rounds effortlessly. 🎯 Focus Mode: Streamline your view for laser-focused due diligence. Zoom in on crucial dates and securities to understand your cap table's journey. 💼 Revolutionize Your Diligence Process: Mantle's Timeline View transforms how founders and lawyers navigate cap tables, saving time and headaches along the way. Learn more ▶️ https://lnkd.in/efKyPYrV #MantleTimelineView #CapTable

News alert: valuation matters today! Our DCF models are an incredibly powerful valuation tool as many of you who’ve seen our Reverse DCF Case studies know (see them here: https://lnkd.in/giE2MqAF). And, I have some news about those models. In case you’ve not seen, the team is hard at work making a lot of cool updates to our website and research tools. One of my favorite is the new charting tools for the Decision Page in our reverse DCF models. Words alone can’t do this update justice; so I put together a short video for everyone to see. Hey, I’m not a video producer, and I’m not getting an Academy awards for this video, but I think it gets the job done. In this short video, I am going to show everyone exactly why Tesla's stock ($TSLA) valuation is ridiculous. I welcome anyone to take the other side of that argument after watching this video. https://lnkd.in/gGN54RMS

Dynamic cash flow modeling means being able to incorporate new assumptions quickly and easily. It reduces manual updates, the likelihood of mistakes while increasing confidence. Here are two great tricks. 1) Dynamic headers and labels In my business models, you commonly see me using dynamic text. This means that the text automatically updates when assumptions change. This helps keep my models current. If you've been experimenting with Copilot, I speculate we'll see this as a built-in feature soon. 2) Dynamic spill ranges Some business modelers and financial modelers cringe when they aren't able to audit every single calculation. But if you build formulas in a way that they never break, you don't have to worry about building overly-simplistic calculations. Here's I use dynamic spill ranges to illustrate the exact values that are being captured in more complex calculations. This results in the best of both worlds -- robust dynamic functionality + auditability. If you missed part 1 of this walkthrough: https://lnkd.in/eZZVBh3U #seidmanfinancial

When we build financial models 📈, there are three key properties that we should try to achieve. 👇 The first two, 𝗙𝗹𝗲𝘅𝗶𝗯𝗶𝗹𝗶𝘁𝘆 and 𝗔𝗱𝗮𝗽𝘁𝗮𝗯𝗶𝗹𝗶𝘁𝘆 are often what modellers put the most effort into: • 🤸 𝗙𝗹𝗲𝘅𝗶𝗯𝗶𝗹𝗶𝘁𝘆 - allowing the user to see best and worst possible outcomes through assumptions that can be easily manipulated to create different scenarios and sensitivities • ✂️ 𝗔𝗱𝗮𝗽𝘁𝗮𝗯𝗶𝗹𝗶𝘁𝘆 - preparing the model in such a way that it can be updated or modified in future, to track outcomes or incorporate new revenue/cost items But these two should never come at the cost of the most important trait: 𝗨𝗻𝗱𝗲𝗿𝘀𝘁𝗮𝗻𝗱𝗮𝗯𝗶𝗹𝗶𝘁𝘆 💡. In fact, by making your model 𝘂𝗻𝗱𝗲𝗿𝘀𝘁𝗮𝗻𝗱𝗮𝗯𝗹𝗲, you will probably go a long way to achieving the first two properties! But what does understandability mean in the context of a model, and why is it so important? The first thing to realise is that a financial model is all about 𝗰𝗼𝗺𝗺𝘂𝗻𝗶𝗰𝗮𝘁𝗶𝗼𝗻. Ultimately when we build any model, we are trying to 𝘀𝘂𝗽𝗽𝗼𝗿𝘁 𝗮𝗻 𝗶𝗻𝗳𝗼𝗿𝗺𝗲𝗱 𝗯𝘂𝘀𝗶𝗻𝗲𝘀𝘀 𝗱𝗲𝗰𝗶𝘀𝗶𝗼𝗻, whether that's investigating the size of a market, assessing the return of a new initiative, or preparing a quote in a bid process. In most cases, the people ultimately making that business decision aren’t the same people building the model. So our model must communicate clearly the answer, yes, but also 𝗵𝗼𝘄 that answer was arrived at. And we’re not just communicating with the 𝗱𝗲𝗰𝗶𝘀𝗶𝗼𝗻-𝗺𝗮𝗸𝗲𝗿. We’re also communicating with: • Our 𝗺𝗮𝗻𝗮𝗴𝗲𝗿, if we have one, who needs to know what we’ve done, and how (and how well!) we’ve done it. • A 𝗳𝘂𝘁𝘂𝗿𝗲 𝗰𝗼𝗹𝗹𝗲𝗮𝗴𝘂𝗲 or 𝗰𝗹𝗶𝗲𝗻𝘁 of ours who needs to edit and maintain the model • 𝗢𝘂𝗿𝘀𝗲𝗹𝘃𝗲𝘀 - how often have you come back to a model that you haven’t looked at for a while and completely forgotten how part of it works?! Creating an 𝘂𝗻𝗱𝗲𝗿𝘀𝘁𝗮𝗻𝗱𝗮𝗯𝗹𝗲 𝗺𝗼𝗱𝗲𝗹 makes that communication so much easier, with all parties. It’s not easy though, even for experienced modellers, so having a set of guidelines (𝘰𝘳 𝘦𝘷𝘦𝘯, 𝘦𝘳, "𝘳𝘶𝘭𝘦𝘴") to work with is super-important. I'll be posting some of mine here in future, but feel free to share yours in the comments!