The travelling salesman chronicles
“Is the travelling salesman problem an NP-hard or an NP easy problem?” our CEO asked one of the new R&D employees at Mobisy.
The non-techies, like me, maintained grave, intelligent expressions, pretending we knew what NP-hard meant.
The reason for his question was that being in the business of transforming supply chain for consumer goods, the ‘travelling salesman’ is truly at the core of the $100Bn CPG Industry in India.
First posed in 1800s, the ‘travelling salesman’ problem still a favorite puzzle amongst developers and mathematicians. You can read about it here.
But why am I telling you about this? Because it’s FMCG’s biggest puzzle too which every brand, including yours, has been trying to solve at some level or other.
The Travelling Salesman in CPG
With thousands of outlets in a single city/town where one retail outlet caters to approximately 25 households, it’s always a balancing act to cover as many outlets as possible and service the top 10-20% of your key outlets which give you up to 60% sales.
So how do you optimize your salesman’s time and effort to ensure that your products are visible and available in as many outlets as possible, ensuring the highest throughput possible.
I sat down with our in-house Data Scientist to get some gyaan on how this works. In between jargon like VRP and knapsack problem he managed to simplify it enough for laymen like me to understand and put it in the context of FMCG. So here’s my breakdown.
Scenario: A city with 30,000 outlets
Quick Math Time
Daily outlets visited per sales rep: 45 (Industry average)
Total outlets covered in a week: 45*6=270
Assuming the brand has a weekly beat system
Total No. of sales reps: 30,000/270= 112. Let’s round it off to a nice sounding number 125.
By using basic logic, one can prioritize outlets depending on sales and optimize this so that the crucial outlets are visited at least once a week. The rest are serviced fortnightly and monthly and so on.
But this has various limitations as the ASM assigning beats manually just cannot take into account multiple parameters and create the ideal beat plan which covers the most outlets in the shortest time while also achieving targets and not missing any key accounts.
(Spoiler: You can increase productivity by upto 40% by simply letting machines do what they’re good at.)
So here’s some of the constraints that an algorithm can take into account to produce the most optimized beat plan.
- The Openers: Just like the right opening combination can pave the path to a great score, the starting and ending point is the most basic parameter which determines a great beat plan. There are cases where companies have extremely low PJP adherence of upto 30% amongst their sales reps simply because they spend far too much time just to get to the first outlet.
- The Googlies: Inactive outlets, duplicate outlets are like those doosras or googlies which leave the batsmen confused as to in which direction to swing the bat. In FMCG, at least 10% outlets mapped in your beats are likely to be inactive and at least 15% are duplicates. These visits add zero business value to a company but add to the workload of the sales rep. Cleaning this up is a big part of creating an effective beat plan.
- The Kohlis: The top outlets which give you the most business have to be serviced regularly and cannot be dropped from the beat (squad). The beat plan should prioritise these key accounts and plan a beat accordingly.
- The Pitch (Real-time conditions): Pitch conditions play a huge role in determining the team you field (as Kohli realized when he fielded the wrong side for the 2nd test). Similarly, real-time traffic conditions, especially in metro cities plays a big role in planning the right beat. You don’t want a sales rep to spend half of his working time travelling to the first outlet. Other conditions taken into account are weather, holidays, any real-time event that can affect a salesperson’s journey
- The Runout (Overlapping Beats): The saddest way to lose your wicket has definitely got to be the runout (Ask Inzamam-ul-Haq or our very own Kaif). It’s even sadder when it’s due to miscommunication resulting in both batsmen ending up on the same side of the crease.
Overlapping beats is one of the biggest causes of an inefficient beat system wherein a sales rep’s beat overlaps with another’s beat on the same day. Or the route he travels in ends up overlapping with an area he’s already covered earlier during the day. Ensuring that the area he covers is unique can reduce duplication of effort by upto 30%.
- The DeVillier Shot: My love for DeVilliers comes from his ability to adapt to any bowling attack and play his shots accordingly. In FMCG, outlets are categorised into various classes depending on the business value. Ensuring that your beat plan covers a right mix of top outlets while servicing the others on a regular basis can be extremely complicated due to the non-linear relationship between them.
With ML-based beat optimization, store-level data is updated regularly and prioritization of outlets is far more dynamic, ensuring your beats are always updated and your products are available at the right outlets.
While all this sounds cool, how do we align this to a brand’s desired outcomes and strategic goals?
Well, depending on what your goals are, the beat plans can change dynamically. So depending on whether outlet growth is a priority, or sales targets is a priority, or you’re looking at a mixture of both, the algorithm can churn out a beat plan most suited to your needs and ensure outcomes are met at a route level.
For eg., If you want a minimum 30 outlets per beat and
To know more about how Bizom’s retail intelligence platform helps you optimize your beats get in touch with us at email@example.com. Also, for those