Supply Chain Analytics

The Bill of Materials is the foundation of raw material planning. But the gap between what the BOM specifies and what procurement actually buys, receives, and uses is where production cost quietly erodes.

FireAI tracks actual raw material consumption against BOM-defined standards at the batch, production order, and product level. Procurement variances, quantity substitutions, and price deviations from the standard are automatically flagged so procurement and production teams can investigate root causes and correct them before they become recurring habits.

What FireAI tracks:

• Actual vs planned raw material consumption per production order (BOM variance %)
• Procurement quantity vs BOM requirement by raw material and supplier
• Price variance: actual purchase price vs standard BOM price, by item and vendor
• Substitution tracking: when alternate materials are used outside BOM specification
• Cumulative variance trend by product family and raw material category
• Financial impact: total material cost overrun vs standard BOM cost for the month

Why BOM variance matters for FMCG manufacturers: An Ahmedabad personal care manufacturer discovered through FireAI that one key emulsifier was consistently being purchased 12-18% above BOM requirements because operators were overcorrecting for process losses. The actual process loss was 4%, but the overcorrection reached 16%. FireAI's raw material procurement analytics dashboard pinpointed the gap, and targeted retraining brought consumption within 2% of BOM standards, saving Rs 6.2 lakh per month in raw material costs.

What you can ask FireAI:

• "Which raw materials had the highest BOM variance last quarter?"
• "Show me procurement vs BOM for our top 10 raw materials this month"
• "What is the total cost impact of BOM overruns in the personal care product line?"

Vendor lead time is one of the most critical inputs in raw material planning, and one of the least accurately tracked. Most procurement teams carry a mental model of lead times established years ago and updated only when a supply crisis forces a conversation.

FireAI builds a live vendor reliability scorecard from your actual purchase order and goods receipt data. Every order placed becomes a data point: when was the PO raised, what lead time did the vendor commit to, when did the material arrive, and by how much did delivery miss the committed window.

What FireAI scores:

• Actual lead time vs promised lead time per vendor, per material, and per order
• On-time delivery rate (%) for each vendor over rolling 30/60/90 day windows
• Lead time variability: average vs standard deviation per vendor, separating consistently late from erratically unreliable vendors
• Partial delivery tracking: how often vendors deliver incomplete quantities vs the PO amount
• Vendor reliability score: composite metric combining on-time rate, quantity accuracy, and lead time consistency
• Production impact: how many production orders were delayed due to late raw material from each vendor

Why vendor lead time tracking matters: A Pune FMCG manufacturer using FireAI discovered that Vendor C had a 94% on-time delivery rate in the ERP record, but the on-time threshold was set to within 5 days of the commitment date. When FireAI recalculated using the actual production need date, the true on-time rate for Vendor C dropped to 61%. The 3-4 day chronic delay from Vendor C had been absorbed by safety stock, masking a real risk. Restructuring the contract with a tighter delivery window and a backup vendor reduced production stoppages from material unavailability by 40% within one quarter.

What you can ask FireAI:

• "Which vendors have the worst on-time delivery rate for critical raw materials?"
• "Show me lead time variability for our top 5 packaging suppliers"
• "How many production orders were impacted by vendor delays this month?"

Inbound quality rejection is the point where raw material risk becomes production risk. A batch of substandard packaging material, an off-spec active ingredient, or a contaminated input can halt an entire production line and require expensive rework or batch disposal.

FireAI tracks every inbound quality inspection result against your acceptance criteria, links rejections to specific suppliers, batches, and purchase orders, and builds a rejection rate profile for every vendor in your supply base. The system identifies patterns in rejection reasons by vendor, material type, and time period so quality and procurement teams can intervene with suppliers before a quality failure becomes a production shutdown.

What FireAI tracks:

• Inbound rejection rate (%) by vendor, by material category, and by month
• Rejection reason breakdown: specification failure, contamination, packaging damage, documentation mismatch
• Batch-level rejection history: every rejected batch linked back to vendor, PO, and inspection result
• Rejection cost tracking: value of rejected material, return freight, and rework or disposal costs
• Trend alerting: vendors whose rejection rate increases across 3 consecutive months are flagged automatically
• Approved vendor status monitoring: vendors approaching rejection thresholds that would trigger AVL review

How FireAI solves the inbound quality problem: A Hyderabad food manufacturer using FireAI identified that Supplier F had maintained a low 2.1% rejection rate for 8 months, then suddenly spiked to 11.4% in two consecutive months. The rejection reason was consistent: moisture content above specification. FireAI traced the pattern to a change in Supplier F's raw material source, which began in the same month as the quality shift. Procurement was able to flag this before the third batch arrived, avoiding a Rs 14.8L production disruption.

What you can ask FireAI:

• "Which suppliers have the highest inbound rejection rate this quarter?"
• "Show me rejection reason breakdown for Supplier F over the last 6 months"
• "What is the total cost of inbound rejections so far this financial year?"

Raw material inventory that sits in the warehouse longer than planned is working capital at rest. The cost of financing excess inventory, the risk of shelf-life breach, and the warehouse space consumed by slow-moving raw materials create a direct and measurable drag on profitability.

FireAI calculates inventory days for every raw material in real time, compares it against planned consumption rates and reorder levels, and flags materials where stock coverage is either too high (slow-moving or over-ordered) or too low (stockout risk). The system also identifies materials approaching shelf-life limits before they become write-off candidates.

What FireAI monitors:

• Inventory days by raw material: current stock divided by average daily consumption
• Slow-moving raw material list: materials with inventory days exceeding 60/90/120-day thresholds
• Reorder level compliance: materials that are being reordered before existing stock is sufficiently depleted
• Shelf-life risk: materials where days-to-expiry is within 30% of inventory days (consumption likely to miss the shelf-life window)
• Carrying cost calculation: financing cost of excess inventory at the company's cost of capital
• Dead stock identification: raw materials with zero movement for 60+ days

FireAI in action: A Mumbai FMCG manufacturer ran FireAI's inventory days analysis and found that 22 raw materials had average inventory days above 90 days, while their production planning assumed 30-day coverage for all materials. The excess stock of Rs 3.1 Cr tied up working capital at a financing cost of Rs 43L per year. Adjusting reorder quantities and reorder points for these 22 materials freed Rs 1.8 Cr in working capital within two procurement cycles.

What you can ask FireAI:

• "Which raw materials have inventory days above 90 days right now?"
• "Show me slow-moving materials with shelf-life risk in the next 60 days"
• "What is the carrying cost of excess raw material inventory this quarter?"