I was having a review of the wonderful sales pacing dash and thinking about targets and forecast.
I'm wondering if/how people have gone about forecasting a final position based on prior performances and what they used in formulas.
eg:
I was keen to play with sames pacing based on an adjusted forecast target.
Can you tell I'm keen for v16 and predictive modeling?
No, just the usual formula
Here's a link to the sisense documentation, if it's helpful. https://docs.sisense.com/main/SisenseLinux/forecasting-future-results.htm#AddingForecaststoWidgetsWhich parameters are you using for "order month" and "Sales", are you in the sales and ticketing cube? I can try to recreate on my end and see if I get the same result.
I am in the Seats and Tickets cube, I'm using 'Order Date' > 'Calendar Month Sort' for the 'Order Month' X-Axis. Sales is 'SUM(Ticket Count)'
Hi Nate - try using Order Date>Date and select Months there.
That did it!
Thank you to you both!
Hi Heath, the predictive modelling sounds exiting!
Something I don't know if you're considering that struck me, as it sounds like you were intending to use averages - with fluctuating season or production run sizes, I think it would also be wise to build in a 'market share' factor in the forecasting. That is, if you grow the number of performances eg by a quarter, you might find the end result of ticket volumes might only have grown by eg a fifth. Just because you put more product out there, doesn't necessarily equate to more people coming in proportion to that. It will depend on the marketplace you're competing in, and the relative popularity of your product/ extra product. Growing market share can take time.
So it might be worth considering a 'market share' factor built into the forecast. We don't do our forecasting in Tessitura yet, but would always bear this in mind if the season / production run size was expanding. Not sure if the predictive modelling in v16 would allow for this, but would be great to hear from others already using it!
So I have a project that I'm working on with my Data and Analytics team to Moneyball our database. If you want to talk about stuff like the potential of using machine learning on 10 years worth of theatre reviews I'll be at TLCC holding that can of worms (hehe)
Hi Melanie, I'm curious to hear how you go about considering market share in your forecast? We've always done this rather un-elegantly by tamping down our total season forecast to not go over what a total season made in the last three years. We figure there's only so many patrons out there buying tickets so we shouldn't expect to grow our revenue without some serious reason to think we could. Especially because being a children's theatre our churn is high.
Analytics and Insights (the artificial intelligence is me )
Heath, this sounds super interesting, would love to chat about this at TLCC. Are you hosting something more formal? otherwise I'm sure i'll run into you!