I am trying to forecast revenue for a HealthTech giant that sales HealthTech Hospital Equipment like Ultrasound, Magnetic resonance, CT AMI etc.

The nature of business is Build to Order, which means at first Orders are booked then different stages like Material planning, production, warehousing, shipment, Delivery, Installation and then finally Invoice Generation which is regarded as Revenue Recognition.

I am working forecasting the monthly Revenue Recognition. Have used Univariate Time Series models taking into account seasonality but MAPE (error) that I am able to get is not so good.

Also, since the final revenue recognition depends a lot upon the previous stages and lead time between Order to Revenue can vary from 2 months to 6 months depending upon types of equipment.

I am slightly confused between Markov Chain or Queuing Theory, which one is likely to be more apt for this.

Looking for some ideas..

  • $\begingroup$ This sounds like a fairly complicated problem to model analytically, especially if the distributions of the lead times of the various stages vary with time. You may want to consider simulation techniques. $\endgroup$ – Math1000 Sep 3 '16 at 1:12

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.