Raw Material Price Forecasting in the Chemicals Industry

Article

Raw Material Price Forecasting in the Chemicals Industry

Improving Conversion on Commodity Business

The chemicals industry is grappling with high volatility in raw materials costs which is impacting margins and competitiveness of businesses. The ability to pass-on volatilities - both upwards and downwards - in a swift and timely manner, dictate the success of businesses operating in highly commoditized and competitive markets. AI and ML driven forecasting and predictive models can help with this.

Challenge

Lack of future visibility into costs of commodities was hampering sales from passing on fluctuations to clients and negatively impacting their conversion and competitive ability.

Sales and pricing departments at Chemical companies with a blockbuster/commoditized portfolio, need a good understanding of the direction in which the base-commodities as well as end-markets are headed. Sourcing, Sales and Pricing departments operating in silos, limited data/insights/information/forecasts on future commodity costs and lack of agility swiftly pass upticks and declines to customers are challenges often seen. Left unaddressed, these can severely hamper the ability of these companies to compete effectively exacerbating the challenge of razor-thin margins. 

Solution

Providing sales with 1-3-6 month commodity forecasts based on built on market data using advanced machine learning techniques and combining this with end-use market demand and willingness-to-pay, enabled them to offer competitive prices to customers.

By combining data with advanced analytics as ensuring information flow b/w different departments, it is possible to improve conversion, competitiveness and margins. Drawing on market data from sources like IHS and ICIS & using advanced machine learning methods, and time-series analysis, forecasting techniques, it is possible to built 1 – 3 – 6 month forecasts on where the base-commodities are headed and how to price them. 

Combining commodity forecasts with information on end-market demand and customer willingness-to-pay can help sales negotiates smarter deals. It can also help purchasing departments negotiate better deals with suppliers.

Impact

Higher deal-win probability and conversion. 

The transparency on the on future commodity prices combined with information on how much the customer was willing to pay, is helping sales make proposals with sharper, market-adjusted pricing which has a higher deal win probability and conversion likelihood. 

Did you find this useful?