iSixSigma

Sales Forecast vs. Actual

Six Sigma – iSixSigma › Forums › Old Forums › Software/IT › Sales Forecast vs. Actual

Viewing 4 posts - 1 through 4 (of 4 total)
  • Author
    Posts
  • January 15, 2007 at 9:16 pm #26574

    Sorour
    ★ 10 Years ★
    Participant

    My current empolyeer is considering implimenting 6sigma which has sparked my interest. This interest has led me to do a fair bit of research and I must say the logic behind 6Sigma is most methodical and intreging.
    I am current a Planner/Buyer with a very dyanamic sales driven company. I already preform a forecast vs. actual analysis in terms of percent but would like to use 6sigma to measure the accuracy. 
    Do I use the unit variance or percent or something else?
    Any sugestions?
    Thank You in Advance. Paul 

    0
    January 16, 2007 at 6:50 am #64605

    gvrk
    ★ 10 Years ★
    Participant

    Paul,
    Good to hear that use of 6sigma for sales. Well we should be sure that when we apply 6sigma for sales forcast due to dynamic variations based on the duration of data collection for analysis the sigma value will be predicted and always there will be a shift of 1.5 sigma from short term sigma to long term sigma value. ie.. ex..let us say u collect the data for a span of 3 months and if u try to arrive at the process capability value (Cpk or sigma value) you may find 5 sigma. If you collect the same data for a span of 1 year and try to measure the process capability value you may find the sigma value as 3.5 sigma..ie.. there is a shift of 1.5.This shift is purely due to dynamic variations which are inherent to the sales forecast process. So do take care of this variation when you are measuring. Coming to your query unit variance will be used if u are considering it as a discrete data ex.. out of 30 sales 10 were sucessfull.. is whether the sale proposed is a win/loss situation. Percent will come if you are considering as continoous data and comparing from the previous to past how much has improved..going back in Jan month 10/30 ie.. 10 were sucesfull out of 30 hence 33% was a succes rate in next month it could be 20/30 (66.67%) here you are collating the info.. and measuring the improvement..I hope this gives you some insight..

    0
    January 16, 2007 at 9:37 am #64606

    Sorour
    ★ 10 Years ★
    Participant

    gvrk,
    Thank you for your reply.
    Being a Planner/Buyer, I deal with the forecast on a SKU/unit level. I have already looked at Cpk using the percent below and setting the UCL to 120% and the LCL to 80%…..calculating the sigma level. It is the zero FC and the zero Actual that tends to create large vaiances.

    SKU
    FC_Jan
    Actual_Jan
    Unit Var.
    Percent

    a
    200
    600
    400
    300%

    b
    0
    100
    100
    10000%

    c
    200
    0
    -200
    0%

    d
    300
    268
    -32
    89%
     
    Is there a better way?
    Thanks …..Paul

    0
    February 2, 2007 at 1:09 pm #64624

    Rhineg
    ★ 10 Years ★
    Member

    I’m glad to see you are collecting data at a detailed level.  Before getting into all of the mechanics, I suggest you back up to “why is a Sales Forecast needed?”  Addressing the multiple answers there will help to focus on which intervals are important and the impact of variability on your company.  e.g.: Sales Forecast are used for:
    predicting cash flow – short term (can we make payroll?)
    raw material purchasing – short term (how much surplus inventory is needed to accommodate uncertainty in how much and which SKUs will be needed?)
    capacity planning – long term (when will we first need the next increment of capacity vs. how long does it take to install and startup that capacity?)

    0
  • Author
    Posts
Viewing 4 posts - 1 through 4 (of 4 total)

The forum ‘Software/IT’ is closed to new topics and replies.