Jump to content

Mahendra Bhandari

Fraternity Members
  • Content Count

  • Joined

  • Last visited

Community Reputation

1 Average

About Mahendra Bhandari

  • Rank
    Advanced Member

Profile Information

  • Company
    Uniparts india limited
  • Designation

Recent Profile Visitors

The recent visitors block is disabled and is not being shown to other users.

  1. To reduce the NCL we firstly look towards the credit assessment and re engineer the process in order to asses the application and to provide the card to the potential right customer. We require eight pieces of information when applying for a credit card: income, education level, age, length of time at current residence, length of time with current employer, savings, debt, and number of credit cards We then look forward to reduce and avoid multi-collinearity or when you have too many predictors relative to the number of observations. Hope it throws some light Regards Mahi
  2. Hi All , I m going to share the use of six sigma beyond process improvement ,that is detecting fraud in accounting data. This tool predicts the frequency of numbers (digits), and hence an anomaly, in naturally-occurring data sets. When used properly, it allows the fact-finder to identify suspect values in a given data set. For example, it is particularly suitable for identifying vendors that submit fraudulent invoices.Using this Rule nonconforming invoice amounts are flagged as systemic errors that corrupt the data set. These fraudulent invoices reveal themselves because the amount (dollar value) does not correspond to a predicable ,This distribution when compared to the other invoice amounts in the sample. It appears that a simple but powerful mathematical phenomena exists that quickly predicts the distribution of numbers for "pointing suspicion at frauds, embezzlers, tax-evaders, sloppy accountants, and even computer bugs." Certain nonrandomly behaved numbers in non-normally distributed data sets (i.e., those that are highly skewed, not uniform in distribution, and not bell-shaped) followed the algorithm defined by: Models the data set against the probability distribution of each digit as itm appears in any number. This is a predictive tool called digital frequency analysis Please read it and let me know if that sounds fruitfull will upload a minitab macro for first digit frequency Thanks Mahi
  3. Hi Abhik, Just look at the cost sheet provided by the sub contractor , check the most hitting figure (priortise those figures based on pareto), focus on cost, if others cost is high definetly need to change the sub contracter , if the processing cost is high . Check the steps followed for processing & most suitably do a VSM (lean). Try to identify the NVA in the processing steps, I,m 100% sure are doing not required steps If u can share the details of the process , surely i will gonna identify the NVA as in garment most of the work is automated . Hope I clarified Thanks, Mahi
  4. Hi Abhik, Are you saying high cost of procurement, can you please bifurcate it further on which cost RM cost Logistics or supply chain Inventory cost Purchase processing cost, etc. That would be required to further provide insights. cheers!!! Mahi
  5. Hello Mr.Rao , Six Sigma can play a vital role in trading feild please let us know a bit brief about WHAT exactly in trading feild Thanks Mahi
  6. Hi Durga, We can certainly use chi square test for a discrete data. As I think I m 2 late to reply on the query of the data discontinuous or discrete. If v r testing defectives the data will follow a binomial distribution (Mr.Niranjan query) And data will be discrete, if v r testing defect data will follow a poison distribution and discrete and if the data is whole number it will be discrete only..... However we can change discrete data into continuous data... adding more as per Mr.Naveen we need to check data theoretically if it's a discrete one or continuous one ...then we need to check the behaviour of data based on distribution then we will do the normality test (if data = Normal) I HAD A QUESTION If the data is continuous then what we will be going to do by identifying the distribution of data, suppose we identified that data is following an exponential distribution y=e^-x , for x>=0 ,standard exponential distribution???? Secondly if the distribution is log normal which have a normally distributed logarithm? Do we still continue to test data for normality???? Warm Regards Mahi
  7. Hi Shijoy , Invoices are scanned in UK and through a server India team receives the invoice - checks for duplicate - key the invoice details to system - and upload the images to system - system does a three way match - matched ones go for payment - unmatched ones go to a different team for resolution - this team contacts UK branches for confirmation or contacts vendor for confirmation - process invoice for payment once the issue is cleared - another team does adjustments in the ledger for the errors - and another team attends to the supplier calls for issues - This is the process in high level this is a paperless accounts payable (PAP), however any system in the AP space cannot exactly identify the fields as vendor name, vendor ID, gross amount, GST etc with an accuracy of 100%, Follow up activity you do is an NVA activity as per my understanding of the process so whatever you receive to do the follow up is an input quality error (cause the system is not able to match the fields and to identify the duplicates), so just map as is process Procedure:- 1) Group a team of 5 ~ 6 persons include SME also 2) Use Collared Post it and Map the process include all the activity irrespective of time frame involved in the activity/task 3) Typically as is mapping an AP process takes 4~6 hrs , break down those activity into Value added , Non Value added , Business Value activity. 4) After AS-IS-MAP , next day take the count of voulme at each activity , number of FTE involved in that Activity , standard time for that activity , Queue time for that activity . 5) After scribing number's , note calculate the process cycle efficiency (PCE)= Value add time / Total time 6) Yours PCE would be typically 0.75% 7) Develop an Kaizen plan for removal of NVA or optimising the NVA try these and let me know what is the outcome / or provide me the above said figures will do the calculation for you then you need to develop Future MAP Apart from VSM what i think that you can take a project for Mistaken payment as possibilty is quite high that vendors are overpaid or the three way match of Gross Amount , Vendor ID & Invoice number do have some accuracy issues correct me if wrong Regards Mahendra
  8. Hi shijoy , surely will help u in perfoming the same in AP process can u give me brief of u r process so that i can design a template for u Regards Mahendra
  9. Hi Guys , If u explain what type of process u r looking into to do a VSM will tell u how to do that one out , i had completed VSM for BFSI & Manufacturing process with tangible imprvement in takt time and process cycle efficiency Regards Mahendra
  10. Gage2.MTW Hi Kiran , attaching a file for GRR let me know if u require any clarification Regards mahendra
  11. Hi Himashu , I agree with your effici.. method of calculation But if u are saying that 4 persons are producing 100 parts per hour than prodcutivity is 25 parts per man hour ... so please answer this question if u want to check which of your manpower/operator is more productive than how will you gonna compare???? Obviously on the basis of the above 25 parts / man/ hour u cannot compare cause as per your formulae all of them are producing 25 parts per hour hence they cannot be compared at all cause they are in the same platform ..... So what you have written is not productivity that is called as production per / person/hour So if u want to calculate productivity you need to have a set of standard time for example Operator A Produces 25 parts in 1 hours against standard time of producing 25 parts in 50 mins Operator B is producing 25 parts in 50 mins against standard time of 25 parts in 50 mins So your operator B is more 100% productive cause he is doing that work in 50 mins as per target hope i calrified you on this topic feel free to revert ...... Regards Mahendra
  12. Hi Anil , Effectiveness is not a quality related term, at any instance OK Quantity / TQ will give u the LOT QUALITY and not LOT EFFECTIVENESS i think that you are talking about overall equipment effectiveness OEE=Availability x Performance x Quality OEE is seperate terminology than effectiveness feel free to corrrect and revert Regards Mahendra
  13. Hi Vikram, Still, the query is incomplete? Six Sigma is applied to a Business case where conventional methods fail, not when u want data analysis in a six sigma way so just to have a six sigma DMAIC approach, first identify for the exact requirement you want the inspection of sites to cost less can u give some bifurcation of the inspection cost directly for example Inspection Site Cost : Concrete testing =$1000 ( Inclusive of Equipment cost) Manhours used / Cost = 40 / $400 Rebar Testing = $500 Profit = $10% of Invoice value Suppose u had done the Inspection of sites Then Manhours used /Cost = 20 / $20 Equipment cost = $ 10000 ( If u r company purchase new equipment amortize that cost ) Similarly another cost, that is my 100% gut feeling that in-house inspection resources for sites will be 30% cheaper than an external agency. Just have a comparison Regards, Mahendra
  14. Hi Vikram, Let me try this way your inspection cost rotates around inspection about civil works ie Foundation of the tower to be erected. Let me share one of my experience with DLF Liang"O" Rourke they earlier are the authorized contractor for DLF residential and commercial building project. Prior to concreting of any activity of the wall / Foundation, we prepare cubes of the concrete and placed it under water for 7,14,21 days. After completion of each of the days, we test the compressive strength as per applicable IS standards. DLF Personel will check the results of the cube compressing strength we had conducted in order to qualify the statement as per the quality plan they had given. If it confirms the requirement the site is good to go else we need to rebuild the whole process from the starting... Hope you get the point Just place a project quality plan in front of the vendor with all the applicable and relevant standards and just check the results submitted by vendor...and do a random site sampling inspection in order to verify the results submitted by the vendor .....i.e Just ask them to keep the extra cubes for the test results they had submitted cause the test results cannot be different for the cubes if the cubes are from the same population and chance become very less that vendor can submit u false information Hope I'm in line with the query you raised. Cheers, Mahi
  15. HI Selvakumar K, Productivity is the speed at which we perform a task with respect to std time ie P=(Task x Std Time)/Total time worked -Diverted time Time worked should be only taken as core work and not diverted work Efficiency is Output/Input x 100 So the basic difference is Productivity is individual capability on certain specifird ste if task and efficiency is capability with all resources included Hope it clarifies thx & Regards Mahi
  • Create New...