**5. Challenges and prospects**

The state of oilseed processing in the tropics leaves much to be desired due to several challenges and large technological gaps which continue to hinder the rapid commercialization of the oilseed processing sector in terms of scale and technology. Although a variety of local technologies are being used in the industry, low utilization of its installed capacity is a challenge. Other challenges include; the lack of modernization in the oilseed processing industry due to inefficient capital machinery, low oil recoveries due to lack of integration between expelling and solvent extraction techniques, lack of standardization of product quality among small-scale processors as most processors produce under non-hygienic conditions without proper monitoring of the quality parameters etc. All this has led to widespread inefficiency in the oilseed processing industry in the tropics which affects domestic markets and export quality.

Furthermore, going by the sustainable development goals of the United Nations, the use of solvent extraction processes in the oilseed processing industry has to take into consideration the health and environmental issues. This in itself is a challenge as alternative and greener solvents have to be used and optimized in the processing of oilseeds while keeping the oil quality intact [28]. Moreover, a sustainable processing methodology and system that has an efficient recovery of the oil fraction from the oilseeds by preserving the quality in an efficient way [29] while eliminating undesirable compounds ought to be adopted.

Nonetheless, despite the several challenges, the sector has massive potential for tremendous growth if various governments introduce special investment incentives for investors and for regulators to monitor and enforce environmental controls and standards. This will lead to the mechanization of bulk handling facilities for enhancing the efficiency of oilseed extractions, development of new value-added products, from the by-products of oilseeds and possibly scientific investigations to machine learning predictive modeling algorithms and simulations for optimization of key parameters necessary to improve oil yield.
