Case Study: Data Analysis Increases Profit for Manufacturer

Case Study: Data Analysis Increases Profit for Manufacturer

August 15, 2018 6:03 pm

My agency is ceaselessly engaged by corporations to research knowledge. One instance is a producer of constructing supplies. The corporate’s revenue was stagnant. It requested us to research gross sales knowledge for patrons, merchandise, and areas to find out the place to focus its marketing efforts and the place to streamline operations, to decrease prices.

On this submit, I’ll describe that engagement and its findings.

Getting ready the Knowledge

The aim of the engagement was easy: to find out methods to extend revenue. To do that, we analyzed gross sales knowledge, together with:

  • Date of sale,
  • Buyer identify or quantity,
  • Vacation spot metropolis and state,
  • SKU or easy product description,
  • Warehouse the place the SKU is saved.

The shopper offered 10 years of knowledge to allow us to evaluate tendencies.

Step one was to organize the info — i.e., manage the segments. That is sometimes finished in a spreadsheet reminiscent of Excel. For the constructing supplies engagement, our course of included:

  • Categorize SKUs by materials, design, and sort. Some merchandise had greater than 10 such attributes.
  • Categorize clients by sort. For instance, enterprise clients might be small unbiased retailers or an enormous field shops. For shopper consumers, we captured family and demographic information, together with gender (from the identify).
  • Categorize ship-to location. Was the vacation spot city or rural? Did clients reside in condos and townhouses in city areas or in indifferent houses in suburban or rural areas?

Operating the Evaluation

The second step was to run the evaluation utilizing numerous analytical fashions, together with cluster evaluation, segmentation evaluation, choice tree modeling, and easy descriptive analytics. You need to use statistical software corresponding to SPSS Statistics or SAS, or programming languages similar to R or Python.

  • Cluster evaluation is the statistical strategy of grouping merchandise by attributes, similar to merchandise which are closest in revenue margins or are fashionable in sure areas.
  • Segmentation evaluation teams clients or merchandise by sort. For instance, one buyer phase could possibly be unbiased contractors. One other might be inside designers. Product varieties could possibly be gadgets for business buildings versus residences. You might additionally group clients geographically, maybe city versus rural.
  • Determination tree modeling is a option to cut up the info into totally different subsets. It sometimes begins with binary splits and continues till there's nothing to separate. For instance, when you set a choice tree to determine clients with probably the most gross sales, you should use it to determine the varieties of merchandise with probably the most gross sales, too.
This hypothetical decision tree shows the split between customer types and the products they ordered with the average size. Big box and retail stores have a higher order size ($2,500) especially for products A, B, C ($5,000). Independent contractors and designers have a lower average order size ($500), especially for products D, A, B ($100).

This hypothetical determination tree exhibits the cut up between buyer varieties and the merchandise ordered with the typical measurement. Massive field and retail shops have a better order measurement ($2,500) particularly for merchandise A, B, C ($5,000). Unbiased contractors and designers have a decrease common order measurement ($500), particularly for merchandise D, A, B ($one hundred).

  • Descriptive analytics is an easy strategy to summarizing historic knowledge by asking questions. Examples embrace “What's the common order measurement?” and “Which sort of consumers (contractors or massive field shops) buy probably the most greenback quantity?” Descriptive evaluation is step one in modeling to see if there's a distinction between clients or merchandise.

Reviewing the Findings

Our evaluation produced the next findings.

  • Worthwhile merchandise. Twenty % of SKUs collectively contributed lower than 1 % of complete gross sales. Subsequently, ceasing the manufacturing of these SKUs would enormously improve revenue.
  • Huge field shops bought a comparatively restricted variety of SKUs, which they ordered in bulk. Huge field shops didn't buy new merchandise. This led to an inner dialogue as to the explanations. Prospects included (a) a scarcity of marketing help for brand spanking new product launches, (b) the necessity to check new merchandise earlier than nationwide rollouts, and (c) the costs of latest merchandise.
  • Unbiased contractors have been a hidden gem, which was sudden. Whereas the portions have been small, they sometimes ordered greater-margin merchandise. Furthermore, unbiased contractors held a lot progress potential. Subsequently, the corporate shifted marketing efforts to this phase of consumers.
  • Inside designers represented lower than zero.01 % of general gross sales. Nevertheless, inside designers steadily ordered the brand new merchandise and in sure areas impacted developments.
  • Geographic influences. There was a transparent distinction amongst geographic markets. Residence interiors differed by area, for instance. Shoppers in California bought totally different merchandise, supplies, and colours than shoppers in Ohio.

The Shock

Combining gross sales and warehouse knowledge uncovered a shock. The corporate had 4 warehouses. Every saved roughly the identical SKUs at comparable portions.

Including geographical preferences to bulk orders from the large field shops and eradicating merchandise that weren't promoting enabled the corporate to economize. Whereas the logistics division was optimizing transit occasions, nobody thought to take a look at the gross sales from every warehouse. However taking a look at geographic preferences, we recognized SKUs which might be wanted for every area and every warehouse, thereby slicing distribution and storage prices.

You may also like...